Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Hiroshi Saruwatari
@article{DBLP:journals/access/XinJTSAS24,
author = {Detai Xin and
Junfeng Jiang and
Shinnosuke Takamichi and
Yuki Saito and
Akiko Aizawa and
Hiroshi Saruwatari},
title = {{JVNV:} {A} Corpus of Japanese Emotional Speech With Verbal Content
and Nonverbal Expressions},
journal = {{IEEE} Access},
volume = {12},
pages = {19752--19764},
year = {2024},
url = {https://doi.org/10.1109/ACCESS.2024.3360885},
doi = {10.1109/ACCESS.2024.3360885},
timestamp = {Sat, 16 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/access/XinJTSAS24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/XinTS24,
author = {Detai Xin and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {{JNV} corpus: {A} corpus of Japanese nonverbal vocalizations with
diverse phrases and emotions},
journal = {Speech Commun.},
volume = {156},
pages = {103004},
year = {2024},
url = {https://doi.org/10.1016/j.specom.2023.103004},
doi = {10.1016/J.SPECOM.2023.103004},
timestamp = {Fri, 08 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/XinTS24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/SaekiMLWTS24,
author = {Takaaki Saeki and
Soumi Maiti and
Xinjian Li and
Shinji Watanabe and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Text-Inductive Graphone-Based Language Adaptation for Low-Resource
Speech Synthesis},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {32},
pages = {1829--1844},
year = {2024},
url = {https://doi.org/10.1109/TASLP.2024.3369537},
doi = {10.1109/TASLP.2024.3369537},
timestamp = {Mon, 01 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/SaekiMLWTS24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-05809,
author = {Yoshihide Tomita and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Localizing Acoustic Energy in Sound Field Synthesis by Directionally
Weighted Exterior Radiation Suppression},
journal = {CoRR},
volume = {abs/2401.05809},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.05809},
doi = {10.48550/ARXIV.2401.05809},
eprinttype = {arXiv},
eprint = {2401.05809},
timestamp = {Fri, 26 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-05809.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-16812,
author = {Takaaki Saeki and
Soumi Maiti and
Shinnosuke Takamichi and
Shinji Watanabe and
Hiroshi Saruwatari},
title = {SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation
Leveraging {NLP} Evaluation Metrics},
journal = {CoRR},
volume = {abs/2401.16812},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.16812},
doi = {10.48550/ARXIV.2401.16812},
eprinttype = {arXiv},
eprint = {2401.16812},
timestamp = {Tue, 06 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-16812.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2403-12477,
author = {Yuto Ishikawa and
Kohei Konaka and
Tomohiko Nakamura and
Norihiro Takamune and
Hiroshi Saruwatari},
title = {Real-time Speech Extraction Using Spatially Regularized Independent
Low-rank Matrix Analysis and Rank-constrained Spatial Covariance Matrix
Estimation},
journal = {CoRR},
volume = {abs/2403.12477},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2403.12477},
doi = {10.48550/ARXIV.2403.12477},
eprinttype = {arXiv},
eprint = {2403.12477},
timestamp = {Mon, 08 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2403-12477.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2403-13353,
author = {Aya Watanabe and
Shinnosuke Takamichi and
Yuki Saito and
Wataru Nakata and
Detai Xin and
Hiroshi Saruwatari},
title = {Building speech corpus with diverse voice characteristics for its
prompt-based representation},
journal = {CoRR},
volume = {abs/2403.13353},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2403.13353},
doi = {10.48550/ARXIV.2403.13353},
eprinttype = {arXiv},
eprint = {2403.13353},
timestamp = {Mon, 08 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2403-13353.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/access/SaekiTNTS23,
author = {Takaaki Saeki and
Shinnosuke Takamichi and
Tomohiko Nakamura and
Naoko Tanji and
Hiroshi Saruwatari},
title = {SelfRemaster: Self-Supervised Speech Restoration for Historical Audio
Resources},
journal = {{IEEE} Access},
volume = {11},
pages = {144831--144843},
year = {2023},
url = {https://doi.org/10.1109/ACCESS.2023.3345027},
doi = {10.1109/ACCESS.2023.3345027},
timestamp = {Sat, 13 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/access/SaekiTNTS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/AbeKUS23,
author = {Takumi Abe and
Shoichi Koyama and
Natsuki Ueno and
Hiroshi Saruwatari},
title = {Amplitude Matching for Multizone Sound Field Control},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {31},
pages = {656--669},
year = {2023},
url = {https://doi.org/10.1109/TASLP.2022.3231715},
doi = {10.1109/TASLP.2022.3231715},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/AbeKUS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/HasumiNTSKTK23,
author = {Takuya Hasumi and
Tomohiko Nakamura and
Norihiro Takamune and
Hiroshi Saruwatari and
Daichi Kitamura and
Yu Takahashi and
Kazunobu Kondo},
title = {PoP-IDLMA: Product-of-Prior Independent Deeply Learned Matrix Analysis
for Multichannel Music Source Separation},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {31},
pages = {2680--2694},
year = {2023},
url = {https://doi.org/10.1109/TASLP.2023.3293044},
doi = {10.1109/TASLP.2023.3293044},
timestamp = {Tue, 12 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/HasumiNTSKTK23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/MisawaTYKS23,
author = {Sota Misawa and
Norihiro Takamune and
Kohei Yatabe and
Daichi Kitamura and
Hiroshi Saruwatari},
title = {Blind Source Separation Using Independent Low-Rank Matrix Analysis
with Spectrogram-Consistency Regularization},
booktitle = {Asia Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2023, Taipei, Taiwan, October
31 - Nov. 3, 2023},
pages = {1050--1057},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/APSIPAASC58517.2023.10317156},
doi = {10.1109/APSIPAASC58517.2023.10317156},
timestamp = {Sat, 02 Dec 2023 14:05:45 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/MisawaTYKS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/WatanabeTSNXS23,
author = {Aya Watanabe and
Shinnosuke Takamichi and
Yuki Saito and
Wataru Nakata and
Detai Xin and
Hiroshi Saruwatari},
title = {{COCO-NUT:} Corpus of Japanese Utterance and Voice Characteristics
Description for Prompt-Based Control},
booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
2023, Taipei, Taiwan, December 16-20, 2023},
pages = {1--8},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ASRU57964.2023.10389693},
doi = {10.1109/ASRU57964.2023.10389693},
timestamp = {Tue, 13 Feb 2024 21:21:14 +0100},
biburl = {https://dblp.org/rec/conf/asru/WatanabeTSNXS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/KojimaAKS23,
author = {Takaaki Kojima and
Kazuyuki Arikawa and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Multichannel Active Noise Control with Exterior Radiation Suppression
Based on Riemannian Optimization},
booktitle = {31st European Signal Processing Conference, {EUSIPCO} 2023, Helsinki,
Finland, September 4-8, 2023},
pages = {96--100},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.23919/EUSIPCO58844.2023.10289919},
doi = {10.23919/EUSIPCO58844.2023.10289919},
timestamp = {Mon, 06 Nov 2023 12:35:15 +0100},
biburl = {https://dblp.org/rec/conf/eusipco/KojimaAKS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/ImamuraNTYS23,
author = {Kanami Imamura and
Tomohiko Nakamura and
Norihiro Takamune and
Kohei Yatabe and
Hiroshi Saruwatari},
title = {Algorithms of Sampling-Frequency-Independent Layers for Non-integer
Strides},
booktitle = {31st European Signal Processing Conference, {EUSIPCO} 2023, Helsinki,
Finland, September 4-8, 2023},
pages = {326--330},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.23919/EUSIPCO58844.2023.10289819},
doi = {10.23919/EUSIPCO58844.2023.10289819},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/eusipco/ImamuraNTYS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/NishidaTIKSN23,
author = {Koki Nishida and
Norihiro Takamune and
Rintaro Ikeshita and
Daichi Kitamura and
Hiroshi Saruwatari and
Tomohiro Nakatani},
title = {NoisyILRMA: Diffuse-Noise-Aware Independent Low-Rank Matrix Analysis
for Fast Blind Source Extraction},
booktitle = {31st European Signal Processing Conference, {EUSIPCO} 2023, Helsinki,
Finland, September 4-8, 2023},
pages = {925--929},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.23919/EUSIPCO58844.2023.10289863},
doi = {10.23919/EUSIPCO58844.2023.10289863},
timestamp = {Mon, 06 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/eusipco/NishidaTIKSN23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ArikawaKS23,
author = {Kazuyuki Arikawa and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Spatial Active Noise Control Method Based on Sound Field Interpolation
from Reference Microphone Signals},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
{ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
pages = {1--5},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ICASSP49357.2023.10097189},
doi = {10.1109/ICASSP49357.2023.10097189},
timestamp = {Sun, 05 Nov 2023 16:51:21 +0100},
biburl = {https://dblp.org/rec/conf/icassp/ArikawaKS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/NakamuraTTFS23,
author = {Tomohiko Nakamura and
Shinnosuke Takamichi and
Naoko Tanji and
Satoru Fukayama and
Hiroshi Saruwatari},
title = {jaCappella Corpus: {A} Japanese a Cappella Vocal Ensemble Corpus},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
{ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
pages = {1--5},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ICASSP49357.2023.10095569},
doi = {10.1109/ICASSP49357.2023.10095569},
timestamp = {Fri, 10 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/NakamuraTTFS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/OhnakaTIOFS23,
author = {Hien Ohnaka and
Shinnosuke Takamichi and
Keisuke Imoto and
Yuki Okamoto and
Kazuki Fujii and
Hiroshi Saruwatari},
title = {Visual Onoma-to-Wave: Environmental Sound Synthesis from Visual Onomatopoeias
and Sound-Source Images},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
{ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
pages = {1--5},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ICASSP49357.2023.10096517},
doi = {10.1109/ICASSP49357.2023.10096517},
timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/OhnakaTIOFS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/RibeiroKS23,
author = {Juliano G. C. Ribeiro and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Kernel Interpolation of Acoustic Transfer Functions with Adaptive
Kernel for Directed and Residual Reverberations},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
{ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
pages = {1--5},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ICASSP49357.2023.10095429},
doi = {10.1109/ICASSP49357.2023.10095429},
timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/RibeiroKS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WatanabeTSXS23,
author = {Aya Watanabe and
Shinnosuke Takamichi and
Yuki Saito and
Detai Xin and
Hiroshi Saruwatari},
title = {MID-Attribute Speaker Generation Using Optimal-Transport-Based Interpolation
of Gaussian Mixture Models},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
{ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
pages = {1--5},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ICASSP49357.2023.10097113},
doi = {10.1109/ICASSP49357.2023.10097113},
timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/WatanabeTSXS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/XinAAKTS23,
author = {Detai Xin and
Sharath Adavanne and
Federico Ang and
Ashish Kulkarni and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Improving Speech Prosody of Audiobook Text-To-Speech Synthesis with
Acoustic and Textual Contexts},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
{ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
pages = {1--5},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ICASSP49357.2023.10096247},
doi = {10.1109/ICASSP49357.2023.10096247},
timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/XinAAKTS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/YangKSSXS23,
author = {Dong Yang and
Tomoki Koriyama and
Yuki Saito and
Takaaki Saeki and
Detai Xin and
Hiroshi Saruwatari},
title = {Duration-Aware Pause Insertion Using Pre-Trained Language Model for
Multi-Speaker Text-To-Speech},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
{ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
pages = {1--5},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ICASSP49357.2023.10096402},
doi = {10.1109/ICASSP49357.2023.10096402},
timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/YangKSSXS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/SaekiML0TS23,
author = {Takaaki Saeki and
Soumi Maiti and
Xinjian Li and
Shinji Watanabe and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech
with Unsupervised Text Pretraining},
booktitle = {Proceedings of the Thirty-Second International Joint Conference on
Artificial Intelligence, {IJCAI} 2023, 19th-25th August 2023, Macao,
SAR, China},
pages = {5179--5187},
publisher = {ijcai.org},
year = {2023},
url = {https://doi.org/10.24963/ijcai.2023/575},
doi = {10.24963/IJCAI.2023/575},
timestamp = {Mon, 28 Aug 2023 17:23:07 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/SaekiML0TS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/waspaa/KimuraKS23,
author = {Keisuke Kimura and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Perceptual Quality Enhancement of Sound Field Synthesis Based on Combination
of Pressure and Amplitude Matching},
booktitle = {{IEEE} Workshop on Applications of Signal Processing to Audio and
Acoustics, {WASPAA} 2023, New Paltz, NY, USA, October 22-25, 2023},
pages = {1--5},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/WASPAA58266.2023.10248106},
doi = {10.1109/WASPAA58266.2023.10248106},
timestamp = {Sat, 23 Sep 2023 11:31:10 +0200},
biburl = {https://dblp.org/rec/conf/waspaa/KimuraKS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/waspaa/KoyamaNRS23,
author = {Shoichi Koyama and
Masaki Nakada and
Juliano G. C. Ribeiro and
Hiroshi Saruwatari},
title = {Kernel Interpolation of Incident Sound Field in Region Including Scattering
Objects},
booktitle = {{IEEE} Workshop on Applications of Signal Processing to Audio and
Acoustics, {WASPAA} 2023, New Paltz, NY, USA, October 22-25, 2023},
pages = {1--5},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/WASPAA58266.2023.10248156},
doi = {10.1109/WASPAA58266.2023.10248156},
timestamp = {Sat, 23 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/waspaa/KoyamaNRS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-12596,
author = {Takaaki Saeki and
Soumi Maiti and
Xinjian Li and
Shinji Watanabe and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech
with Unsupervised Text Pretraining},
journal = {CoRR},
volume = {abs/2301.12596},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.12596},
doi = {10.48550/ARXIV.2301.12596},
eprinttype = {arXiv},
eprint = {2301.12596},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-12596.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-13652,
author = {Dong Yang and
Tomoki Koriyama and
Yuki Saito and
Takaaki Saeki and
Detai Xin and
Hiroshi Saruwatari},
title = {Duration-aware pause insertion using pre-trained language model for
multi-speaker text-to-speech},
journal = {CoRR},
volume = {abs/2302.13652},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.13652},
doi = {10.48550/ARXIV.2302.13652},
eprinttype = {arXiv},
eprint = {2302.13652},
timestamp = {Tue, 28 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-13652.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-03869,
author = {Juliano G. C. Ribeiro and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Kernel interpolation of acoustic transfer functions with adaptive
kernel for directed and residual reverberations},
journal = {CoRR},
volume = {abs/2303.03869},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2303.03869},
doi = {10.48550/ARXIV.2303.03869},
eprinttype = {arXiv},
eprint = {2303.03869},
timestamp = {Thu, 16 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2303-03869.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-16021,
author = {Kazuyuki Arikawa and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Spatial Active Noise Control Method Based On Sound Field Interpolation
From Reference Microphone Signals},
journal = {CoRR},
volume = {abs/2303.16021},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2303.16021},
doi = {10.48550/ARXIV.2303.16021},
eprinttype = {arXiv},
eprint = {2303.16021},
timestamp = {Thu, 13 Apr 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2303-16021.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-12442,
author = {Detai Xin and
Shinnosuke Takamichi and
Ai Morimatsu and
Hiroshi Saruwatari},
title = {Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale
In-the-wild Laughter Corpus},
journal = {CoRR},
volume = {abs/2305.12442},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.12442},
doi = {10.48550/ARXIV.2305.12442},
eprinttype = {arXiv},
eprint = {2305.12442},
timestamp = {Fri, 26 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-12442.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-12445,
author = {Detai Xin and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {{JNV} Corpus: {A} Corpus of Japanese Nonverbal Vocalizations with
Diverse Phrases and Emotions},
journal = {CoRR},
volume = {abs/2305.12445},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.12445},
doi = {10.48550/ARXIV.2305.12445},
eprinttype = {arXiv},
eprint = {2305.12445},
timestamp = {Fri, 26 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-12445.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-13713,
author = {Yuki Saito and
Eiji Iimori and
Shinnosuke Takamichi and
Kentaro Tachibana and
Hiroshi Saruwatari},
title = {{CALLS:} Japanese Empathetic Dialogue Speech Corpus of Complaint Handling
and Attentive Listening in Customer Center},
journal = {CoRR},
volume = {abs/2305.13713},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.13713},
doi = {10.48550/ARXIV.2305.13713},
eprinttype = {arXiv},
eprint = {2305.13713},
timestamp = {Mon, 05 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-13713.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-13724,
author = {Yuki Saito and
Shinnosuke Takamichi and
Eiji Iimori and
Kentaro Tachibana and
Hiroshi Saruwatari},
title = {ChatGPT-EDSS: Empathetic Dialogue Speech Synthesis Trained from ChatGPT-derived
Context Word Embeddings},
journal = {CoRR},
volume = {abs/2305.13724},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.13724},
doi = {10.48550/ARXIV.2305.13724},
eprinttype = {arXiv},
eprint = {2305.13724},
timestamp = {Mon, 05 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-13724.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-00697,
author = {Joonyong Park and
Shinnosuke Takamichi and
Tomohiko Nakamura and
Kentaro Seki and
Detai Xin and
Hiroshi Saruwatari},
title = {How Generative Spoken Language Modeling Encodes Noisy Speech: Investigation
from Phonetics to Syntactics},
journal = {CoRR},
volume = {abs/2306.00697},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.00697},
doi = {10.48550/ARXIV.2306.00697},
eprinttype = {arXiv},
eprint = {2306.00697},
timestamp = {Mon, 12 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-00697.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-08855,
author = {Takaaki Kojima and
Kazuyuki Arikawa and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Multichannel Active Noise Control with Exterior Radiation Suppression
Based on Riemannian Optimization},
journal = {CoRR},
volume = {abs/2306.08855},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.08855},
doi = {10.48550/ARXIV.2306.08855},
eprinttype = {arXiv},
eprint = {2306.08855},
timestamp = {Mon, 19 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-08855.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-10718,
author = {Kanami Imamura and
Tomohiko Nakamura and
Norihiro Takamune and
Kohei Yatabe and
Hiroshi Saruwatari},
title = {Algorithms of Sampling-Frequency-Independent Layers for Non-integer
Strides},
journal = {CoRR},
volume = {abs/2306.10718},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.10718},
doi = {10.48550/ARXIV.2306.10718},
eprinttype = {arXiv},
eprint = {2306.10718},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-10718.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-12169,
author = {Yota Ueda and
Shinnosuke Takamichi and
Yuki Saito and
Norihiro Takamune and
Hiroshi Saruwatari},
title = {HumanDiffusion: diffusion model using perceptual gradients},
journal = {CoRR},
volume = {abs/2306.12169},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.12169},
doi = {10.48550/ARXIV.2306.12169},
eprinttype = {arXiv},
eprint = {2306.12169},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-12169.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-12820,
author = {Koki Nishida and
Norihiro Takamune and
Rintaro Ikeshita and
Daichi Kitamura and
Hiroshi Saruwatari and
Tomohiro Nakatani},
title = {NoisyILRMA: Diffuse-Noise-Aware Independent Low-Rank Matrix Analysis
for Fast Blind Source Extraction},
journal = {CoRR},
volume = {abs/2306.12820},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.12820},
doi = {10.48550/ARXIV.2306.12820},
eprinttype = {arXiv},
eprint = {2306.12820},
timestamp = {Tue, 27 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-12820.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-13941,
author = {Keisuke Kimura and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Perceptual Quality Enhancement of Sound Field Synthesis Based on Combination
of Pressure and Amplitude Matching},
journal = {CoRR},
volume = {abs/2307.13941},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.13941},
doi = {10.48550/ARXIV.2307.13941},
eprinttype = {arXiv},
eprint = {2307.13941},
timestamp = {Tue, 01 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-13941.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-05634,
author = {Shoichi Koyama and
Masaki Nakada and
Juliano G. C. Ribeiro and
Hiroshi Saruwatari},
title = {Kernel Interpolation of Incident Sound Field in Region Including Scattering
Objects},
journal = {CoRR},
volume = {abs/2309.05634},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.05634},
doi = {10.48550/ARXIV.2309.05634},
eprinttype = {arXiv},
eprint = {2309.05634},
timestamp = {Fri, 15 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-05634.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-08127,
author = {Kentaro Seki and
Shinnosuke Takamichi and
Takaaki Saeki and
Hiroshi Saruwatari},
title = {Diversity-based core-set selection for text-to-speech with linguistic
and acoustic features},
journal = {CoRR},
volume = {abs/2309.08127},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.08127},
doi = {10.48550/ARXIV.2309.08127},
eprinttype = {arXiv},
eprint = {2309.08127},
timestamp = {Fri, 22 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-08127.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-09690,
author = {Shinnosuke Takamichi and
Hiroki Maeda and
Joonyong Park and
Daisuke Saito and
Hiroshi Saruwatari},
title = {Do learned speech symbols follow Zipf's law?},
journal = {CoRR},
volume = {abs/2309.09690},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.09690},
doi = {10.48550/ARXIV.2309.09690},
eprinttype = {arXiv},
eprint = {2309.09690},
timestamp = {Fri, 22 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-09690.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-13509,
author = {Aya Watanabe and
Shinnosuke Takamichi and
Yuki Saito and
Wataru Nakata and
Detai Xin and
Hiroshi Saruwatari},
title = {Coco-Nut: Corpus of Japanese Utterance and Voice Characteristics Description
for Prompt-based Control},
journal = {CoRR},
volume = {abs/2309.13509},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.13509},
doi = {10.48550/ARXIV.2309.13509},
eprinttype = {arXiv},
eprint = {2309.13509},
timestamp = {Wed, 27 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-13509.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-06072,
author = {Detai Xin and
Junfeng Jiang and
Shinnosuke Takamichi and
Yuki Saito and
Akiko Aizawa and
Hiroshi Saruwatari},
title = {{JVNV:} {A} Corpus of Japanese Emotional Speech with Verbal Content
and Nonverbal Expressions},
journal = {CoRR},
volume = {abs/2310.06072},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.06072},
doi = {10.48550/ARXIV.2310.06072},
eprinttype = {arXiv},
eprint = {2310.06072},
timestamp = {Tue, 24 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-06072.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ejasp/KondoKTKS22,
author = {Yuto Kondo and
Yuki Kubo and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari},
title = {Deficient-basis-complementary rank-constrained spatial covariance
matrix estimation based on multivariate generalized Gaussian distribution
for blind speech extraction},
journal = {{EURASIP} J. Adv. Signal Process.},
volume = {2022},
number = {1},
pages = {88},
year = {2022},
url = {https://doi.org/10.1186/s13634-022-00905-z},
doi = {10.1186/S13634-022-00905-Z},
timestamp = {Mon, 05 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ejasp/KondoKTKS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/SaitoNYS22,
author = {Koichi Saito and
Tomohiko Nakamura and
Kohei Yatabe and
Hiroshi Saruwatari},
title = {Sampling-Frequency-Independent Convolutional Layer and its Application
to Audio Source Separation},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {30},
pages = {2928--2943},
year = {2022},
url = {https://doi.org/10.1109/TASLP.2022.3203907},
doi = {10.1109/TASLP.2022.3203907},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/SaitoNYS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/RibeiroUKS22,
author = {Juliano G. C. Ribeiro and
Natsuki Ueno and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Region-to-Region Kernel Interpolation of Acoustic Transfer Functions
Constrained by Physical Properties},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {30},
pages = {2944--2954},
year = {2022},
url = {https://doi.org/10.1109/TASLP.2022.3201368},
doi = {10.1109/TASLP.2022.3201368},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/RibeiroUKS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsp/NishidaUKS22,
author = {Tomoya Nishida and
Natsuki Ueno and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Region-Restricted Sensor Placement Based on Gaussian Process for Sound
Field Estimation},
journal = {{IEEE} Trans. Signal Process.},
volume = {70},
pages = {1718--1733},
year = {2022},
url = {https://doi.org/10.1109/TSP.2022.3156012},
doi = {10.1109/TSP.2022.3156012},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tsp/NishidaUKS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/RibeiroKS22,
author = {Juliano G. C. Ribeiro and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Region-to-Region Kernel Interpolation of Acoustic Transfer Function
with Directional Weighting},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
pages = {576--580},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ICASSP43922.2022.9746842},
doi = {10.1109/ICASSP43922.2022.9746842},
timestamp = {Tue, 07 Jun 2022 17:34:47 +0200},
biburl = {https://dblp.org/rec/conf/icassp/RibeiroKS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KawamuraNKSTK22,
author = {Masaya Kawamura and
Tomohiko Nakamura and
Daichi Kitamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Differentiable Digital Signal Processing Mixture Model for Synthesis
Parameter Extraction from Mixture of Harmonic Sounds},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
pages = {941--945},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ICASSP43922.2022.9746399},
doi = {10.1109/ICASSP43922.2022.9746399},
timestamp = {Thu, 23 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KawamuraNKSTK22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ArikawaKS22,
author = {Kazuyuki Arikawa and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Spatial Active Noise Control Based on Individual Kernel Interpolation
of Primary and Secondary Sound Fields},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
pages = {1056--1060},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ICASSP43922.2022.9746065},
doi = {10.1109/ICASSP43922.2022.9746065},
timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ArikawaKS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TakamichiNTS22,
author = {Shinnosuke Takamichi and
Wataru Nakata and
Naoko Tanji and
Hiroshi Saruwatari},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {{J-MAC:} Japanese multi-speaker audiobook corpus for speech synthesis},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {2358--2362},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-444},
doi = {10.21437/INTERSPEECH.2022-444},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/TakamichiNTS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/UdagawaSS22,
author = {Kenta Udagawa and
Yuki Saito and
Hiroshi Saruwatari},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Human-in-the-loop Speaker Adaptation for DNN-based Multi-speaker {TTS}},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {2968--2972},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-257},
doi = {10.21437/INTERSPEECH.2022-257},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/UdagawaSS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NishimuraSTTS22,
author = {Yuto Nishimura and
Yuki Saito and
Shinnosuke Takamichi and
Kentaro Tachibana and
Hiroshi Saruwatari},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Acoustic Modeling for End-to-End Empathetic Dialogue Speech Synthesis
Using Linguistic and Prosodic Contexts of Dialogue History},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {3373--3377},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-403},
doi = {10.21437/INTERSPEECH.2022-403},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/NishimuraSTTS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaekiTNTS22,
author = {Takaaki Saeki and
Shinnosuke Takamichi and
Tomohiko Nakamura and
Naoko Tanji and
Hiroshi Saruwatari},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {SelfRemaster: Self-Supervised Speech Restoration with Analysis-by-Synthesis
Approach Using Channel Modeling},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {4406--4410},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-298},
doi = {10.21437/INTERSPEECH.2022-298},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaekiTNTS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaekiXNKTS22,
author = {Takaaki Saeki and
Detai Xin and
Wataru Nakata and
Tomoki Koriyama and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {{UTMOS:} UTokyo-SaruLab System for VoiceMOS Challenge 2022},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {4521--4525},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-439},
doi = {10.21437/INTERSPEECH.2022-439},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaekiXNKTS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NakataKTSIMS22,
author = {Wataru Nakata and
Tomoki Koriyama and
Shinnosuke Takamichi and
Yuki Saito and
Yusuke Ijima and
Ryo Masumura and
Hiroshi Saruwatari},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Predicting VQVAE-based Character Acting Style from Quotation-Annotated
Text for Audiobook Speech Synthesis},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {4551--4555},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-638},
doi = {10.21437/INTERSPEECH.2022-638},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/NakataKTSIMS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaitoNTTS22,
author = {Yuki Saito and
Yuto Nishimura and
Shinnosuke Takamichi and
Kentaro Tachibana and
Hiroshi Saruwatari},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {{STUDIES:} Corpus of Japanese Empathetic Dialogue Speech Towards Friendly
Voice Agent},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {5155--5159},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-300},
doi = {10.21437/INTERSPEECH.2022-300},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaitoNTTS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwaenc/ItoNKS22,
author = {Yuki Ito and
Tomohiko Nakamura and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Head-Related Transfer Function Interpolation From Spatially Sparse
Measurements Using Autoencoder With Source Position Conditioning},
booktitle = {17th International Workshop on Acoustic Signal Enhancement, {IWAENC}
2022, Bamberg, Germany, September 5-8, 2022},
pages = {1--5},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/IWAENC53105.2022.9914751},
doi = {10.1109/IWAENC53105.2022.9914751},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iwaenc/ItoNKS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwaenc/ShigemiKNS22,
author = {Kazuhide Shigemi and
Shoichi Koyama and
Tomohiko Nakamura and
Hiroshi Saruwatari},
title = {Physics-Informed Convolutional Neural Network with Bicubic Spline
Interpolation for Sound Field Estimation},
booktitle = {17th International Workshop on Acoustic Signal Enhancement, {IWAENC}
2022, Bamberg, Germany, September 5-8, 2022},
pages = {1--5},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/IWAENC53105.2022.9914792},
doi = {10.1109/IWAENC53105.2022.9914792},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iwaenc/ShigemiKNS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/lrec/MatsunagaSTS22,
author = {Yuta Matsunaga and
Takaaki Saeki and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
editor = {Nicoletta Calzolari and
Fr{\'{e}}d{\'{e}}ric B{\'{e}}chet and
Philippe Blache and
Khalid Choukri and
Christopher Cieri and
Thierry Declerck and
Sara Goggi and
Hitoshi Isahara and
Bente Maegaard and
Joseph Mariani and
H{\'{e}}l{\`{e}}ne Mazo and
Jan Odijk and
Stelios Piperidis},
title = {Personalized Filled-pause Generation with Group-wise Prediction Models},
booktitle = {Proceedings of the Thirteenth Language Resources and Evaluation Conference,
{LREC} 2022, Marseille, France, 20-25 June 2022},
pages = {385--392},
publisher = {European Language Resources Association},
year = {2022},
url = {https://aclanthology.org/2022.lrec-1.40},
timestamp = {Mon, 10 Oct 2022 16:57:52 +0200},
biburl = {https://dblp.org/rec/conf/lrec/MatsunagaSTS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/NakanoSTSS22,
author = {Yoshifumi Nakano and
Takaaki Saeki and
Shinnosuke Takamichi and
Katsuhito Sudoh and
Hiroshi Saruwatari},
title = {{VTTS:} Visual-Text To Speech},
booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2022, Doha, Qatar,
January 9-12, 2023},
pages = {936--942},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/SLT54892.2023.10022739},
doi = {10.1109/SLT54892.2023.10022739},
timestamp = {Mon, 06 Feb 2023 22:19:30 +0100},
biburl = {https://dblp.org/rec/conf/slt/NakanoSTSS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-10896,
author = {Shinnosuke Takamichi and
Wataru Nakata and
Naoko Tanji and
Hiroshi Saruwatari},
title = {{J-MAC:} Japanese multi-speaker audiobook corpus for speech synthesis},
journal = {CoRR},
volume = {abs/2201.10896},
year = {2022},
url = {https://arxiv.org/abs/2201.10896},
eprinttype = {arXiv},
eprint = {2201.10896},
timestamp = {Tue, 01 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-10896.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-00200,
author = {Masaya Kawamura and
Tomohiko Nakamura and
Daichi Kitamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Differentiable Digital Signal Processing Mixture Model for Synthesis
Parameter Extraction from Mixture of Harmonic Sounds},
journal = {CoRR},
volume = {abs/2202.00200},
year = {2022},
url = {https://arxiv.org/abs/2202.00200},
eprinttype = {arXiv},
eprint = {2202.00200},
timestamp = {Wed, 09 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-00200.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-04807,
author = {Kazuyuki Arikawa and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Spatial active noise control based on individual kernel interpolation
of primary and secondary sound fields},
journal = {CoRR},
volume = {abs/2202.04807},
year = {2022},
url = {https://arxiv.org/abs/2202.04807},
eprinttype = {arXiv},
eprint = {2202.04807},
timestamp = {Tue, 01 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-04807.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-09961,
author = {Yuta Matsunaga and
Takaaki Saeki and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Personalized filled-pause generation with group-wise prediction models},
journal = {CoRR},
volume = {abs/2203.09961},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.09961},
doi = {10.48550/ARXIV.2203.09961},
eprinttype = {arXiv},
eprint = {2203.09961},
timestamp = {Mon, 28 Mar 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-09961.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-12937,
author = {Takaaki Saeki and
Shinnosuke Takamichi and
Tomohiko Nakamura and
Naoko Tanji and
Hiroshi Saruwatari},
title = {SelfRemaster: Self-Supervised Speech Restoration with Analysis-by-Synthesis
Approach Using Channel Modeling},
journal = {CoRR},
volume = {abs/2203.12937},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.12937},
doi = {10.48550/ARXIV.2203.12937},
eprinttype = {arXiv},
eprint = {2203.12937},
timestamp = {Tue, 29 Mar 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-12937.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-14725,
author = {Yoshifumi Nakano and
Takaaki Saeki and
Shinnosuke Takamichi and
Katsuhito Sudoh and
Hiroshi Saruwatari},
title = {vTTS: visual-text to speech},
journal = {CoRR},
volume = {abs/2203.14725},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.14725},
doi = {10.48550/ARXIV.2203.14725},
eprinttype = {arXiv},
eprint = {2203.14725},
timestamp = {Mon, 04 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-14725.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-14757,
author = {Yuki Saito and
Yuto Nishimura and
Shinnosuke Takamichi and
Kentaro Tachibana and
Hiroshi Saruwatari},
title = {{STUDIES:} Corpus of Japanese Empathetic Dialogue Speech Towards Friendly
Voice Agent},
journal = {CoRR},
volume = {abs/2203.14757},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.14757},
doi = {10.48550/ARXIV.2203.14757},
eprinttype = {arXiv},
eprint = {2203.14757},
timestamp = {Mon, 04 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-14757.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-02152,
author = {Takaaki Saeki and
Detai Xin and
Wataru Nakata and
Tomoki Koriyama and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {{UTMOS:} UTokyo-SaruLab System for VoiceMOS Challenge 2022},
journal = {CoRR},
volume = {abs/2204.02152},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.02152},
doi = {10.48550/ARXIV.2204.02152},
eprinttype = {arXiv},
eprint = {2204.02152},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-02152.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-10561,
author = {Detai Xin and
Shinnosuke Takamichi and
Takuma Okamoto and
Hisashi Kawai and
Hiroshi Saruwatari},
title = {Speaking-Rate-Controllable HiFi-GAN Using Feature Interpolation},
journal = {CoRR},
volume = {abs/2204.10561},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.10561},
doi = {10.48550/ARXIV.2204.10561},
eprinttype = {arXiv},
eprint = {2204.10561},
timestamp = {Mon, 25 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-10561.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-08039,
author = {Yuto Nishimura and
Yuki Saito and
Shinnosuke Takamichi and
Kentaro Tachibana and
Hiroshi Saruwatari},
title = {Acoustic Modeling for End-to-End Empathetic Dialogue Speech Synthesis
Using Linguistic and Prosodic Contexts of Dialogue History},
journal = {CoRR},
volume = {abs/2206.08039},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.08039},
doi = {10.48550/ARXIV.2206.08039},
eprinttype = {arXiv},
eprint = {2206.08039},
timestamp = {Tue, 21 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-08039.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-10256,
author = {Kenta Udagawa and
Yuki Saito and
Hiroshi Saruwatari},
title = {Human-in-the-loop Speaker Adaptation for DNN-based Multi-speaker {TTS}},
journal = {CoRR},
volume = {abs/2206.10256},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.10256},
doi = {10.48550/ARXIV.2206.10256},
eprinttype = {arXiv},
eprint = {2206.10256},
timestamp = {Mon, 27 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-10256.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-10695,
author = {Detai Xin and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Exploring the Effectiveness of Self-supervised Learning and Classifier
Chains in Emotion Recognition of Nonverbal Vocalizations},
journal = {CoRR},
volume = {abs/2206.10695},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.10695},
doi = {10.48550/ARXIV.2206.10695},
eprinttype = {arXiv},
eprint = {2206.10695},
timestamp = {Mon, 27 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-10695.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-10937,
author = {Kazuhide Shigemi and
Shoichi Koyama and
Tomohiko Nakamura and
Hiroshi Saruwatari},
title = {Physics-informed convolutional neural network with bicubic spline
interpolation for sound field estimation},
journal = {CoRR},
volume = {abs/2207.10937},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2207.10937},
doi = {10.48550/ARXIV.2207.10937},
eprinttype = {arXiv},
eprint = {2207.10937},
timestamp = {Mon, 25 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2207-10937.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-10967,
author = {Yuki Ito and
Tomohiko Nakamura and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Head-Related Transfer Function Interpolation from Spatially Sparse
Measurements Using Autoencoder with Source Position Conditioning},
journal = {CoRR},
volume = {abs/2207.10967},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2207.10967},
doi = {10.48550/ARXIV.2207.10967},
eprinttype = {arXiv},
eprint = {2207.10967},
timestamp = {Mon, 25 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2207-10967.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-12549,
author = {Yusuke Nakai and
Yuki Saito and
Kenta Udagawa and
Hiroshi Saruwatari},
title = {Multi-Task Adversarial Training Algorithm for Multi-Speaker Neural
Text-to-Speech},
journal = {CoRR},
volume = {abs/2209.12549},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.12549},
doi = {10.48550/ARXIV.2209.12549},
eprinttype = {arXiv},
eprint = {2209.12549},
timestamp = {Thu, 06 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-12549.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-07559,
author = {Yuta Matsunaga and
Takaaki Saeki and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Empirical Study Incorporating Linguistic Knowledge on Filled Pauses
for Personalized Spontaneous Speech Synthesis},
journal = {CoRR},
volume = {abs/2210.07559},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.07559},
doi = {10.48550/ARXIV.2210.07559},
eprinttype = {arXiv},
eprint = {2210.07559},
timestamp = {Tue, 18 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-07559.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-09173,
author = {Hien Ohnaka and
Shinnosuke Takamichi and
Keisuke Imoto and
Yuki Okamoto and
Kazuki Fujii and
Hiroshi Saruwatari},
title = {Visual onoma-to-wave: environmental sound synthesis from visual onomatopoeias
and sound-source images},
journal = {CoRR},
volume = {abs/2210.09173},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.09173},
doi = {10.48550/ARXIV.2210.09173},
eprinttype = {arXiv},
eprint = {2210.09173},
timestamp = {Wed, 19 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-09173.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-09815,
author = {Yuta Matsunaga and
Takaaki Saeki and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Spontaneous speech synthesis with linguistic-speech consistency training
using pseudo-filled pauses},
journal = {CoRR},
volume = {abs/2210.09815},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.09815},
doi = {10.48550/ARXIV.2210.09815},
eprinttype = {arXiv},
eprint = {2210.09815},
timestamp = {Mon, 24 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-09815.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-09916,
author = {Aya Watanabe and
Shinnosuke Takamichi and
Yuki Saito and
Detai Xin and
Hiroshi Saruwatari},
title = {Mid-attribute speaker generation using optimal-transport-based interpolation
of Gaussian mixture models},
journal = {CoRR},
volume = {abs/2210.09916},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.09916},
doi = {10.48550/ARXIV.2210.09916},
eprinttype = {arXiv},
eprint = {2210.09916},
timestamp = {Mon, 24 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-09916.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-14850,
author = {Kentaro Seki and
Shinnosuke Takamichi and
Takaaki Saeki and
Hiroshi Saruwatari},
title = {Text-to-speech synthesis from dark data with evaluation-in-the-loop
data selection},
journal = {CoRR},
volume = {abs/2210.14850},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.14850},
doi = {10.48550/ARXIV.2210.14850},
eprinttype = {arXiv},
eprint = {2210.14850},
timestamp = {Wed, 02 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-14850.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-02336,
author = {Detai Xin and
Sharath Adavanne and
Federico Ang and
Ashish Kulkarni and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Improving Speech Prosody of Audiobook Text-to-Speech Synthesis with
Acoustic and Textual Contexts},
journal = {CoRR},
volume = {abs/2211.02336},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.02336},
doi = {10.48550/ARXIV.2211.02336},
eprinttype = {arXiv},
eprint = {2211.02336},
timestamp = {Wed, 09 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-02336.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-16028,
author = {Tomohiko Nakamura and
Shinnosuke Takamichi and
Naoko Tanji and
Satoru Fukayama and
Hiroshi Saruwatari},
title = {jaCappella Corpus: {A} Japanese a Cappella Vocal Ensemble Corpus},
journal = {CoRR},
volume = {abs/2211.16028},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.16028},
doi = {10.48550/ARXIV.2211.16028},
eprinttype = {arXiv},
eprint = {2211.16028},
timestamp = {Fri, 02 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-16028.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieiceta/UenoKS21,
author = {Natsuki Ueno and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Convex and Differentiable Formulation for Inverse Problems in Hilbert
Spaces with Nonlinear Clipping Effects},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {104-A},
number = {9},
pages = {1293--1303},
year = {2021},
url = {https://doi.org/10.1587/transfun.2021eap1004},
doi = {10.1587/TRANSFUN.2021EAP1004},
timestamp = {Thu, 12 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieiceta/UenoKS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicetd/AibaYKTS21,
author = {Akihito Aiba and
Minoru Yoshida and
Daichi Kitamura and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Noise Robust Acoustic Anomaly Detection System with Nonnegative Matrix
Factorization Based on Generalized Gaussian Distribution},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {104-D},
number = {3},
pages = {441--449},
year = {2021},
url = {http://search.ieice.org/bin/summary.php?id=e104-d\_3\_441},
timestamp = {Mon, 17 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicetd/AibaYKTS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicetd/SaekiSTS21,
author = {Takaaki Saeki and
Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Real-Time Full-Band Voice Conversion with Sub-Band Modeling and Data-Driven
Phase Estimation of Spectral Differentials},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {104-D},
number = {7},
pages = {1002--1016},
year = {2021},
url = {https://doi.org/10.1587/transinf.2020edp7252},
doi = {10.1587/TRANSINF.2020EDP7252},
timestamp = {Thu, 12 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicetd/SaekiSTS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicetd/MizoguchiSTS21,
author = {Satoshi Mizoguchi and
Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {DNN-Based Low-Musical-Noise Single-Channel Speech Enhancement Based
on Higher-Order-Moments Matching},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {104-D},
number = {11},
pages = {1971--1980},
year = {2021},
url = {https://doi.org/10.1587/transinf.2021edp7041},
doi = {10.1587/TRANSINF.2021EDP7041},
timestamp = {Thu, 12 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicetd/MizoguchiSTS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sigpro/MakishimaMTKSTK21,
author = {Naoki Makishima and
Yoshiki Mitsui and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Independent deeply learned matrix analysis with automatic selection
of stable microphone-wise update and fast sourcewise update of demixing
matrix},
journal = {Signal Process.},
volume = {178},
pages = {107753},
year = {2021},
url = {https://doi.org/10.1016/j.sigpro.2020.107753},
doi = {10.1016/J.SIGPRO.2020.107753},
timestamp = {Fri, 14 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/sigpro/MakishimaMTKSTK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sigpro/KamoMKTKSTK21,
author = {Keigo Kamo and
Yoshiki Mitsui and
Yuki Kubo and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Joint-diagonalizability-constrained multichannel nonnegative matrix
factorization based on time-variant multivariate complex sub-Gaussian
distribution},
journal = {Signal Process.},
volume = {188},
pages = {108183},
year = {2021},
url = {https://doi.org/10.1016/j.sigpro.2021.108183},
doi = {10.1016/J.SIGPRO.2021.108183},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/sigpro/KamoMKTKSTK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/MitsuiKS21,
author = {Kentaro Mitsui and
Tomoki Koriyama and
Hiroshi Saruwatari},
title = {Deep Gaussian process based multi-speaker speech synthesis with latent
speaker representation},
journal = {Speech Commun.},
volume = {132},
pages = {132--145},
year = {2021},
url = {https://doi.org/10.1016/j.specom.2021.07.001},
doi = {10.1016/J.SPECOM.2021.07.001},
timestamp = {Fri, 13 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/speech/MitsuiKS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spl/SaekiTS21,
author = {Takaaki Saeki and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Incremental Text-to-Speech Synthesis Using Pseudo Lookahead With Large
Pretrained Language Model},
journal = {{IEEE} Signal Process. Lett.},
volume = {28},
pages = {857--861},
year = {2021},
url = {https://doi.org/10.1109/LSP.2021.3073869},
doi = {10.1109/LSP.2021.3073869},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/spl/SaekiTS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/MitsufujiTKS21,
author = {Yuki Mitsufuji and
Norihiro Takamune and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Multichannel Blind Source Separation Based on Evanescent-Region-Aware
Non-Negative Tensor Factorization in Spherical Harmonic Domain},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {29},
pages = {607--617},
year = {2021},
url = {https://doi.org/10.1109/TASLP.2020.3045528},
doi = {10.1109/TASLP.2020.3045528},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/MitsufujiTKS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/SaitoTS21,
author = {Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Perceptual-Similarity-Aware Deep Speaker Representation Learning for
Multi-Speaker Generative Modeling},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {29},
pages = {1033--1048},
year = {2021},
url = {https://doi.org/10.1109/TASLP.2021.3059114},
doi = {10.1109/TASLP.2021.3059114},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/SaitoTS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/NakamuraKS21,
author = {Tomohiko Nakamura and
Shihori Kozuka and
Hiroshi Saruwatari},
title = {Time-Domain Audio Source Separation With Neural Networks Based on
Multiresolution Analysis},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {29},
pages = {1687--1701},
year = {2021},
url = {https://doi.org/10.1109/TASLP.2021.3072496},
doi = {10.1109/TASLP.2021.3072496},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/NakamuraKS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/KoyamaBIUS21,
author = {Shoichi Koyama and
Jesper Brunnstr{\"{o}}m and
Hayato Ito and
Natsuki Ueno and
Hiroshi Saruwatari},
title = {Spatial Active Noise Control Based on Kernel Interpolation of Sound
Field},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {29},
pages = {3052--3063},
year = {2021},
url = {https://doi.org/10.1109/TASLP.2021.3107983},
doi = {10.1109/TASLP.2021.3107983},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/KoyamaBIUS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsp/UenoKS21,
author = {Natsuki Ueno and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Directionally Weighted Wave Field Estimation Exploiting Prior Information
on Source Direction},
journal = {{IEEE} Trans. Signal Process.},
volume = {69},
pages = {2383--2395},
year = {2021},
url = {https://doi.org/10.1109/TSP.2021.3070228},
doi = {10.1109/TSP.2021.3070228},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tsp/UenoKS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/MisawaTNKSUM21,
author = {Sota Misawa and
Norihiro Takamune and
Tomohiko Nakamura and
Daichi Kitamura and
Hiroshi Saruwatari and
Masakazu Une and
Shoji Makino},
title = {Speech Enhancement by Noise Self-Supervised Rank-Constrained Spatial
Covariance Matrix Estimation via Independent Deeply Learned Matrix
Analysis},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2021, Tokyo, Japan, December
14-17, 2021},
pages = {578--584},
publisher = {{IEEE}},
year = {2021},
url = {https://ieeexplore.ieee.org/document/9689665},
timestamp = {Wed, 09 Feb 2022 09:03:08 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/MisawaTNKSUM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/MizobuchiKNSTK21,
author = {Yusaku Mizobuchi and
Daichi Kitamura and
Tomohiko Nakamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Prior Distribution Design for Music Bleeding-Sound Reduction Based
on Nonnegative Matrix Factorization},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2021, Tokyo, Japan, December
14-17, 2021},
pages = {651--658},
publisher = {{IEEE}},
year = {2021},
url = {https://ieeexplore.ieee.org/document/9689601},
timestamp = {Wed, 09 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/MizobuchiKNSTK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/LuoTKSS21,
author = {Xuan Luo and
Shinnosuke Takamichi and
Tomoki Koriyama and
Yuki Saito and
Hiroshi Saruwatari},
title = {Emotion-Controllable Speech Synthesis Using Emotion Soft Labels and
Fine-Grained Prosody Factors},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2021, Tokyo, Japan, December
14-17, 2021},
pages = {794--799},
publisher = {{IEEE}},
year = {2021},
url = {https://ieeexplore.ieee.org/document/9689217},
timestamp = {Wed, 09 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/LuoTKSS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/HasumiNTSKTK21,
author = {Takuya Hasumi and
Tomohiko Nakamura and
Norihiro Takamune and
Hiroshi Saruwatari and
Daichi Kitamura and
Yu Takahashi and
Kazunobu Kondo},
title = {Multichannel Audio Source Separation with Independent Deeply Learned
Matrix Analysis Using Product of Source Models},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2021, Tokyo, Japan, December
14-17, 2021},
pages = {1226--1233},
publisher = {{IEEE}},
year = {2021},
url = {https://ieeexplore.ieee.org/document/9689636},
timestamp = {Sun, 22 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/HasumiNTSKTK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/SaekiTS21,
author = {Takaaki Saeki and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Low-Latency Incremental Text-to-Speech Synthesis with Distilled Context
Prediction Network},
booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
2021, Cartagena, Colombia, December 13-17, 2021},
pages = {749--756},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ASRU51503.2021.9687904},
doi = {10.1109/ASRU51503.2021.9687904},
timestamp = {Wed, 09 Feb 2022 09:03:03 +0100},
biburl = {https://dblp.org/rec/conf/asru/SaekiTS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/SaitoNYKS21,
author = {Koichi Saito and
Tomohiko Nakamura and
Kohei Yatabe and
Yuma Koizumi and
Hiroshi Saruwatari},
title = {Sampling-Frequency-Independent Audio Source Separation Using Convolution
Layer Based on Impulse Invariant Method},
booktitle = {29th European Signal Processing Conference, {EUSIPCO} 2021, Dublin,
Ireland, August 23-27, 2021},
pages = {321--325},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.23919/EUSIPCO54536.2021.9615941},
doi = {10.23919/EUSIPCO54536.2021.9615941},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/eusipco/SaitoNYKS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/NarisawaITKNSN21,
author = {Naoki Narisawa and
Rintaro Ikeshita and
Norihiro Takamune and
Daichi Kitamura and
Tomohiko Nakamura and
Hiroshi Saruwatari and
Tomohiro Nakatani},
title = {Independent Deeply Learned Tensor Analysis for Determined Audio Source
Separation},
booktitle = {29th European Signal Processing Conference, {EUSIPCO} 2021, Dublin,
Ireland, August 23-27, 2021},
pages = {326--330},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.23919/EUSIPCO54536.2021.9616300},
doi = {10.23919/EUSIPCO54536.2021.9616300},
timestamp = {Mon, 03 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/eusipco/NarisawaITKNSN21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/HasumiNTSKTK21,
author = {Takuya Hasumi and
Tomohiko Nakamura and
Norihiro Takamune and
Hiroshi Saruwatari and
Daichi Kitamura and
Yu Takahashi and
Kazunobu Kondo},
title = {Empirical Bayesian Independent Deeply Learned Matrix Analysis For
Multichannel Audio Source Separation},
booktitle = {29th European Signal Processing Conference, {EUSIPCO} 2021, Dublin,
Ireland, August 23-27, 2021},
pages = {331--335},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.23919/EUSIPCO54536.2021.9616245},
doi = {10.23919/EUSIPCO54536.2021.9616245},
timestamp = {Mon, 03 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/eusipco/HasumiNTSKTK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KoyamaAUS21,
author = {Shoichi Koyama and
Takashi Amakasu and
Natsuki Ueno and
Hiroshi Saruwatari},
title = {Amplitude Matching: Majorization-Minimization Algorithm for Sound
Field Control Only with Amplitude Constraint},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {411--415},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414855},
doi = {10.1109/ICASSP39728.2021.9414855},
timestamp = {Thu, 08 Jul 2021 17:12:48 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KoyamaAUS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KondoKTKS21,
author = {Yuto Kondo and
Yuki Kubo and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari},
title = {Deficient Basis Estimation of Noise Spatial Covariance Matrix for
Rank-Constrained Spatial Covariance Matrix Estimation Method in Blind
Speech Extraction},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {806--810},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414479},
doi = {10.1109/ICASSP39728.2021.9414479},
timestamp = {Thu, 08 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KondoKTKS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/UedaFSTBS21,
author = {Yota Ueda and
Kazuki Fujii and
Yuki Saito and
Shinnosuke Takamichi and
Yukino Baba and
Hiroshi Saruwatari},
title = {Humanacgan: Conditional Generative Adversarial Network with Human-Based
Auxiliary Classifier and its Evaluation in Phoneme Perception},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {6468--6472},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9413363},
doi = {10.1109/ICASSP39728.2021.9413363},
timestamp = {Fri, 09 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/UedaFSTBS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/XinKTS21,
author = {Detai Xin and
Tatsuya Komatsu and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Disentangled Speaker and Language Representations Using Mutual Information
Minimization and Domain Adaptation for Cross-Lingual {TTS}},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {6608--6612},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414226},
doi = {10.1109/ICASSP39728.2021.9414226},
timestamp = {Fri, 09 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/XinKTS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NakamuraKS21,
author = {Taiki Nakamura and
Tomoki Koriyama and
Hiroshi Saruwatari},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Sequence-to-Sequence Learning for Deep Gaussian Process Based Speech
Synthesis Using Self-Attention {GP} Layer},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {121--125},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-896},
doi = {10.21437/INTERSPEECH.2021-896},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/NakamuraKS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/XinSTKS21,
author = {Detai Xin and
Yuki Saito and
Shinnosuke Takamichi and
Tomoki Koriyama and
Hiroshi Saruwatari},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Cross-Lingual Speaker Adaptation Using Domain Adaptation and Speaker
Consistency Loss for Text-To-Speech Synthesis},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {1614--1618},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-897},
doi = {10.21437/INTERSPEECH.2021-897},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/XinSTKS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MizutaKS21,
author = {Kazuki Mizuta and
Tomoki Koriyama and
Hiroshi Saruwatari},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Harmonic WaveGAN: GAN-Based Speech Waveform Generation Model with
Harmonic Structure Discriminator},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {2192--2196},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-583},
doi = {10.21437/INTERSPEECH.2021-583},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MizutaKS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/waspaa/HoriuchiKRUS21,
author = {Ryosuke Horiuchi and
Shoichi Koyama and
Juliano G. C. Ribeiro and
Natsuki Ueno and
Hiroshi Saruwatari},
title = {Kernel Learning for Sound Field Estimation with {L1} and {L2} Regularizations},
booktitle = {{IEEE} Workshop on Applications of Signal Processing to Audio and
Acoustics, {WASPAA} 2021, New Paltz, NY, USA, October 17-20, 2021},
pages = {261--265},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/WASPAA52581.2021.9632731},
doi = {10.1109/WASPAA52581.2021.9632731},
timestamp = {Tue, 21 Dec 2021 10:11:15 +0100},
biburl = {https://dblp.org/rec/conf/waspaa/HoriuchiKRUS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/waspaa/KimuraKUS21,
author = {Keisuke Kimura and
Shoichi Koyama and
Natsuki Ueno and
Hiroshi Saruwatari},
title = {Mean-Square-Error-Based Secondary Source Placement in Sound Field
Synthesis with Prior Information on Desired Field},
booktitle = {{IEEE} Workshop on Applications of Signal Processing to Audio and
Acoustics, {WASPAA} 2021, New Paltz, NY, USA, October 17-20, 2021},
pages = {281--285},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/WASPAA52581.2021.9632799},
doi = {10.1109/WASPAA52581.2021.9632799},
timestamp = {Tue, 21 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/waspaa/KimuraKUS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-04051,
author = {Yota Ueda and
Kazuki Fujii and
Yuki Saito and
Shinnosuke Takamichi and
Yukino Baba and
Hiroshi Saruwatari},
title = {HumanACGAN: conditional generative adversarial network with human-based
auxiliary classifier and its evaluation in phoneme perception},
journal = {CoRR},
volume = {abs/2102.04051},
year = {2021},
url = {https://arxiv.org/abs/2102.04051},
eprinttype = {arXiv},
eprint = {2102.04051},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-04051.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2105-02491,
author = {Yuto Kondo and
Yuki Kubo and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari},
title = {Deficient Basis Estimation of Noise Spatial Covariance Matrix for
Rank-Constrained Spatial Covariance Matrix Estimation Method in Blind
Speech Extraction},
journal = {CoRR},
volume = {abs/2105.02491},
year = {2021},
url = {https://arxiv.org/abs/2105.02491},
eprinttype = {arXiv},
eprint = {2105.02491},
timestamp = {Wed, 12 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2105-02491.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2105-04079,
author = {Koichi Saito and
Tomohiko Nakamura and
Kohei Yatabe and
Yuma Koizumi and
Hiroshi Saruwatari},
title = {Sampling-Frequency-Independent Audio Source Separation Using Convolution
Layer Based on Impulse Invariant Method},
journal = {CoRR},
volume = {abs/2105.04079},
year = {2021},
url = {https://arxiv.org/abs/2105.04079},
eprinttype = {arXiv},
eprint = {2105.04079},
timestamp = {Fri, 14 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2105-04079.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-03492,
author = {Takuya Hasumi and
Tomohiko Nakamura and
Norihiro Takamune and
Hiroshi Saruwatari and
Daichi Kitamura and
Yu Takahashi and
Kazunobu Kondo},
title = {Empirical Bayesian Independent Deeply Learned Matrix Analysis For
Multichannel Audio Source Separation},
journal = {CoRR},
volume = {abs/2106.03492},
year = {2021},
url = {https://arxiv.org/abs/2106.03492},
eprinttype = {arXiv},
eprint = {2106.03492},
timestamp = {Thu, 10 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-03492.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-05529,
author = {Naoki Narisawa and
Rintaro Ikeshita and
Norihiro Takamune and
Daichi Kitamura and
Tomohiko Nakamura and
Hiroshi Saruwatari and
Tomohiro Nakatani},
title = {Independent Deeply Learned Tensor Analysis for Determined Audio Source
Separation},
journal = {CoRR},
volume = {abs/2106.05529},
year = {2021},
url = {https://arxiv.org/abs/2106.05529},
eprinttype = {arXiv},
eprint = {2106.05529},
timestamp = {Tue, 15 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-05529.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-00237,
author = {Yusaku Mizobuchi and
Daichi Kitamura and
Tomohiko Nakamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Prior Distribution Design for Music Bleeding-Sound Reduction Based
on Nonnegative Matrix Factorization},
journal = {CoRR},
volume = {abs/2109.00237},
year = {2021},
url = {https://arxiv.org/abs/2109.00237},
eprinttype = {arXiv},
eprint = {2109.00237},
timestamp = {Mon, 20 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-00237.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-00704,
author = {Takuya Hasumi and
Tomohiko Nakamura and
Norihiro Takamune and
Hiroshi Saruwatari and
Daichi Kitamura and
Yu Takahashi and
Kazunobu Kondo},
title = {Multichannel Audio Source Separation with Independent Deeply Learned
Matrix Analysis Using Product of Source Models},
journal = {CoRR},
volume = {abs/2109.00704},
year = {2021},
url = {https://arxiv.org/abs/2109.00704},
eprinttype = {arXiv},
eprint = {2109.00704},
timestamp = {Mon, 20 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-00704.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-04658,
author = {Sota Misawa and
Norihiro Takamune and
Tomohiko Nakamura and
Daichi Kitamura and
Hiroshi Saruwatari and
Masakazu Une and
Shoji Makino},
title = {Speech Enhancement by Noise Self-Supervised Rank-Constrained Spatial
Covariance Matrix Estimation via Independent Deeply Learned Matrix
Analysis},
journal = {CoRR},
volume = {abs/2109.04658},
year = {2021},
url = {https://arxiv.org/abs/2109.04658},
eprinttype = {arXiv},
eprint = {2109.04658},
timestamp = {Tue, 21 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-04658.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-07274,
author = {Naoto Iijima and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Binaural rendering from microphone array signals of arbitrary geometry},
journal = {CoRR},
volume = {abs/2109.07274},
year = {2021},
url = {https://arxiv.org/abs/2109.07274},
eprinttype = {arXiv},
eprint = {2109.07274},
timestamp = {Wed, 22 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-07274.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-10724,
author = {Takaaki Saeki and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Low-Latency Incremental Text-to-Speech Synthesis with Distilled Context
Prediction Network},
journal = {CoRR},
volume = {abs/2109.10724},
year = {2021},
url = {https://arxiv.org/abs/2109.10724},
eprinttype = {arXiv},
eprint = {2109.10724},
timestamp = {Mon, 27 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-10724.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-04972,
author = {Ryosuke Horiuchi and
Shoichi Koyama and
Juliano G. C. Ribeiro and
Natsuki Ueno and
Hiroshi Saruwatari},
title = {Kernel Learning For Sound Field Estimation With {L1} and {L2} Regularizations},
journal = {CoRR},
volume = {abs/2110.04972},
year = {2021},
url = {https://arxiv.org/abs/2110.04972},
eprinttype = {arXiv},
eprint = {2110.04972},
timestamp = {Thu, 21 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-04972.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-06774,
author = {Keisuke Kimura and
Shoichi Koyama and
Natsuki Ueno and
Hiroshi Saruwatari},
title = {Mean-square-error-based secondary source placement in sound field
synthesis with prior information on desired field},
journal = {CoRR},
volume = {abs/2112.06774},
year = {2021},
url = {https://arxiv.org/abs/2112.06774},
eprinttype = {arXiv},
eprint = {2112.06774},
timestamp = {Mon, 03 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-06774.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/TamaruSTKS20,
author = {Hiroki Tamaru and
Yuki Saito and
Shinnosuke Takamichi and
Tomoki Koriyama and
Hiroshi Saruwatari},
title = {Generative Moment Matching Network-Based Neural Double-Tracking for
Synthesized and Natural Singing Voices},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {103-D},
number = {3},
pages = {639--647},
year = {2020},
url = {http://search.ieice.org/bin/summary.php?id=e103-d\_3\_639},
doi = {10.1587/TRANSINF.2019EDP7228},
timestamp = {Mon, 06 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ieicet/TamaruSTKS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicetd/KoguchiTMSS20,
author = {Junya Koguchi and
Shinnosuke Takamichi and
Masanori Morise and
Hiroshi Saruwatari and
Shigeki Sagayama},
title = {DNN-Based Full-Band Speech Synthesis Using {GMM} Approximation of
Spectral Envelope},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {103-D},
number = {12},
pages = {2673--2681},
year = {2020},
url = {https://doi.org/10.1587/transinf.2020EDP7075},
doi = {10.1587/TRANSINF.2020EDP7075},
timestamp = {Mon, 18 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ieicetd/KoguchiTMSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sigpro/TakamichiSTKS20,
author = {Shinnosuke Takamichi and
Yuki Saito and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari},
title = {Phase reconstruction from amplitude spectrograms based on directional-statistics
deep neural networks},
journal = {Signal Process.},
volume = {169},
pages = {107368},
year = {2020},
url = {https://doi.org/10.1016/j.sigpro.2019.107368},
doi = {10.1016/J.SIGPRO.2019.107368},
timestamp = {Fri, 14 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/sigpro/TakamichiSTKS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sigpro/TakidaKUS20,
author = {Yuhta Takida and
Shoichi Koyama and
Natsuki Ueno and
Hiroshi Saruwatari},
title = {Reciprocity gap functional in spherical harmonic domain for gridless
sound field decomposition},
journal = {Signal Process.},
volume = {169},
pages = {107383},
year = {2020},
url = {https://doi.org/10.1016/j.sigpro.2019.107383},
doi = {10.1016/J.SIGPRO.2019.107383},
timestamp = {Fri, 14 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/sigpro/TakidaKUS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/AsoTTS20,
author = {Masashi Aso and
Shinnosuke Takamichi and
Norihiro Takamune and
Hiroshi Saruwatari},
title = {Acoustic model-based subword tokenization and prosodic-context extraction
without language knowledge for text-to-speech synthesis},
journal = {Speech Commun.},
volume = {125},
pages = {53--60},
year = {2020},
url = {https://doi.org/10.1016/j.specom.2020.09.003},
doi = {10.1016/J.SPECOM.2020.09.003},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/speech/AsoTTS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/MitsufujiUTKKS20,
author = {Yuki Mitsufuji and
Stefan Uhlich and
Norihiro Takamune and
Daichi Kitamura and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Multichannel Non-Negative Matrix Factorization Using Banded Spatial
Covariance Matrices in Wavenumber Domain},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {28},
pages = {49--60},
year = {2020},
url = {https://doi.org/10.1109/TASLP.2019.2948770},
doi = {10.1109/TASLP.2019.2948770},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/MitsufujiUTKKS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/MogamiTKSTKO20,
author = {Shinichi Mogami and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo and
Nobutaka Ono},
title = {Independent Low-Rank Matrix Analysis Based on Time-Variant Sub-Gaussian
Source Model for Determined Blind Source Separation},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {28},
pages = {503--518},
year = {2020},
url = {https://doi.org/10.1109/TASLP.2019.2959257},
doi = {10.1109/TASLP.2019.2959257},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/MogamiTKSTKO20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/KuboTKS20,
author = {Yuki Kubo and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari},
title = {Blind Speech Extraction Based on Rank-Constrained Spatial Covariance
Matrix Estimation With Multivariate Generalized Gaussian Distribution},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {28},
pages = {1948--1963},
year = {2020},
url = {https://doi.org/10.1109/TASLP.2020.3003165},
doi = {10.1109/TASLP.2020.3003165},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/KuboTKS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/KamoKTKSTK20,
author = {Keigo Kamo and
Yuki Kubo and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Joint-Diagonalizability-Constrained Multichannel Nonnegative Matrix
Factorization Based on Multivariate Complex Student's t-distribution},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2020, Auckland, New Zealand, December
7-10, 2020},
pages = {869--874},
publisher = {{IEEE}},
year = {2020},
url = {https://ieeexplore.ieee.org/document/9306489},
timestamp = {Thu, 11 Feb 2021 11:44:30 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/KamoKTKSTK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/WatanabeKSTK20,
author = {Rui Watanabe and
Daichi Kitamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {DNN-Based Frequency Component Prediction for Frequency-Domain Audio
Source Separation},
booktitle = {28th European Signal Processing Conference, {EUSIPCO} 2020, Amsterdam,
Netherlands, January 18-21, 2021},
pages = {805--809},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.23919/Eusipco47968.2020.9287225},
doi = {10.23919/EUSIPCO47968.2020.9287225},
timestamp = {Fri, 08 Jan 2021 16:18:38 +0100},
biburl = {https://dblp.org/rec/conf/eusipco/WatanabeKSTK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/KamoKTKSTK20,
author = {Keigo Kamo and
Yuki Kubo and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Joint-Diagonalizability-Constrained Multichannel Nonnegative Matrix
Factorization Based on Multivariate Complex Sub-Gaussian Distribution},
booktitle = {28th European Signal Processing Conference, {EUSIPCO} 2020, Amsterdam,
Netherlands, January 18-21, 2021},
pages = {890--894},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.23919/Eusipco47968.2020.9287572},
doi = {10.23919/EUSIPCO47968.2020.9287572},
timestamp = {Fri, 08 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/eusipco/KamoKTKSTK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/NishidaUKS20,
author = {Tomoya Nishida and
Natsuki Ueno and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Sensor placement in arbitrarily restricted region for field estimation
based on Gaussian process},
booktitle = {28th European Signal Processing Conference, {EUSIPCO} 2020, Amsterdam,
Netherlands, January 18-21, 2021},
pages = {2289--2293},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.23919/Eusipco47968.2020.9287222},
doi = {10.23919/EUSIPCO47968.2020.9287222},
timestamp = {Fri, 08 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/eusipco/NishidaUKS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ArigaNKUS20,
author = {Kentaro Ariga and
Tomoya Nishida and
Shoichi Koyama and
Natsuki Ueno and
Hiroshi Saruwatari},
title = {Mutual-Information-Based Sensor Placement for Spatial Sound Field
Recording},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {166--170},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9053715},
doi = {10.1109/ICASSP40776.2020.9053715},
timestamp = {Thu, 23 Jul 2020 16:19:28 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ArigaNKUS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/NakamuraS20,
author = {Tomohiko Nakamura and
Hiroshi Saruwatari},
title = {Time-Domain Audio Source Separation Based on Wave-U-Net Combined with
Discrete Wavelet Transform},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {386--390},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9053934},
doi = {10.1109/ICASSP40776.2020.9053934},
timestamp = {Sat, 05 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/NakamuraS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KamoKTKSTK20,
author = {Keigo Kamo and
Yuki Kubo and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Regularized Fast Multichannel Nonnegative Matrix Factorization with
ILRMA-Based Prior Distribution of Joint-Diagonalization Process},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {606--610},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9054603},
doi = {10.1109/ICASSP40776.2020.9054603},
timestamp = {Thu, 23 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KamoKTKSTK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KondoFTKSIN20,
author = {Tatsuki Kondo and
Kanta Fukushige and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari and
Rintaro Ikeshita and
Tomohiro Nakatani},
title = {Convergence-Guaranteed Independent Positive Semidefinite Tensor Analysis
Based on Student's {T} Distribution},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {681--685},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9054150},
doi = {10.1109/ICASSP40776.2020.9054150},
timestamp = {Thu, 23 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KondoFTKSIN20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/FujiiSTBS20,
author = {Kazuki Fujii and
Yuki Saito and
Shinnosuke Takamichi and
Yukino Baba and
Hiroshi Saruwatari},
title = {Humangan: Generative Adversarial Network With Human-Based Discriminator
And Its Evaluation In Speech Perception Modeling},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {6239--6243},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9053844},
doi = {10.1109/ICASSP40776.2020.9053844},
timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/FujiiSTBS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KoriyamaS20,
author = {Tomoki Koriyama and
Hiroshi Saruwatari},
title = {Utterance-Level Sequential Modeling for Deep Gaussian Process Based
Speech Synthesis Using Simple Recurrent Unit},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {7249--7253},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9052935},
doi = {10.1109/ICASSP40776.2020.9052935},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/KoriyamaS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaekiSTS20,
author = {Takaaki Saeki and
Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Lifter Training and Sub-Band Modeling for Computationally Efficient
and High-Quality Voice Conversion Using Spectral Differentials},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {7784--7788},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9054490},
doi = {10.1109/ICASSP40776.2020.9054490},
timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SaekiSTS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ItoKUS20,
author = {Hayato Ito and
Shoichi Koyama and
Natsuki Ueno and
Hiroshi Saruwatari},
title = {Spatial Active Noise Control Based on Kernel Interpolation with Directional
Weighting},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {8404--8408},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9053416},
doi = {10.1109/ICASSP40776.2020.9053416},
timestamp = {Thu, 23 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ItoKUS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ieeesam/RibeiroUKS20,
author = {Juliano G. C. Ribeiro and
Natsuki Ueno and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Kernel interpolation of acoustic transfer function between regions
considering reciprocity},
booktitle = {11th {IEEE} Sensor Array and Multichannel Signal Processing Workshop,
{SAM} 2020, Hangzhou, China, June 8-11, 2020},
pages = {1--5},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/SAM48682.2020.9104256},
doi = {10.1109/SAM48682.2020.9104256},
timestamp = {Tue, 15 Jun 2021 19:37:23 +0200},
biburl = {https://dblp.org/rec/conf/ieeesam/RibeiroUKS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TakeuchiKOS20,
author = {Hirotoshi Takeuchi and
Kunio Kashino and
Yasunori Ohishi and
Hiroshi Saruwatari},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Harmonic Lowering for Accelerating Harmonic Convolution for Audio
Signals},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {185--189},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-3185},
doi = {10.21437/INTERSPEECH.2020-3185},
timestamp = {Fri, 29 Jan 2021 17:40:16 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/TakeuchiKOS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaekiSTS20,
author = {Takaaki Saeki and
Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Real-Time, Full-Band, Online DNN-Based Voice Conversion System Using
a Single {CPU}},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {1021--1022},
publisher = {{ISCA}},
year = {2020},
url = {https://www.isca-speech.org/archive/interspeech\_2020/saeki20\_interspeech.html},
timestamp = {Tue, 27 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaekiSTS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MitsuiKS20,
author = {Kentaro Mitsui and
Tomoki Koriyama and
Hiroshi Saruwatari},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Multi-Speaker Text-to-Speech Synthesis Using Deep Gaussian Processes},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {2032--2036},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-3167},
doi = {10.21437/INTERSPEECH.2020-3167},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/MitsuiKS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/XinSTKS20,
author = {Detai Xin and
Yuki Saito and
Shinnosuke Takamichi and
Tomoki Koriyama and
Hiroshi Saruwatari},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Cross-Lingual Text-To-Speech Synthesis via Domain Adaptation and Perceptual
Similarity Regression in Speaker Space},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {2947--2951},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-2070},
doi = {10.21437/INTERSPEECH.2020-2070},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/XinSTKS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/YamashitaKSTIMS20,
author = {Yuki Yamashita and
Tomoki Koriyama and
Yuki Saito and
Shinnosuke Takamichi and
Yusuke Ijima and
Ryo Masumura and
Hiroshi Saruwatari},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Investigating Effective Additional Contextual Factors in DNN-Based
Spontaneous Speech Synthesis},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {3201--3205},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-2469},
doi = {10.21437/INTERSPEECH.2020-2469},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/YamashitaKSTIMS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AsoTS20,
author = {Masashi Aso and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {End-to-End Text-to-Speech Synthesis with Unaligned Multiple Language
Units Based on Attention},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {4009--4013},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-2347},
doi = {10.21437/INTERSPEECH.2020-2347},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/AsoTS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/lrec/YamashitaKSTIMS20,
author = {Yuki Yamashita and
Tomoki Koriyama and
Yuki Saito and
Shinnosuke Takamichi and
Yusuke Ijima and
Ryo Masumura and
Hiroshi Saruwatari},
editor = {Nicoletta Calzolari and
Fr{\'{e}}d{\'{e}}ric B{\'{e}}chet and
Philippe Blache and
Khalid Choukri and
Christopher Cieri and
Thierry Declerck and
Sara Goggi and
Hitoshi Isahara and
Bente Maegaard and
Joseph Mariani and
H{\'{e}}l{\`{e}}ne Mazo and
Asunci{\'{o}}n Moreno and
Jan Odijk and
Stelios Piperidis},
title = {DNN-based Speech Synthesis Using Abundant Tags of Spontaneous Speech
Corpus},
booktitle = {Proceedings of The 12th Language Resources and Evaluation Conference,
{LREC} 2020, Marseille, France, May 11-16, 2020},
pages = {6438--6443},
publisher = {European Language Resources Association},
year = {2020},
url = {https://aclanthology.org/2020.lrec-1.792/},
timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/lrec/YamashitaKSTIMS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/lrec/SaitoTS20,
author = {Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
editor = {Nicoletta Calzolari and
Fr{\'{e}}d{\'{e}}ric B{\'{e}}chet and
Philippe Blache and
Khalid Choukri and
Christopher Cieri and
Thierry Declerck and
Sara Goggi and
Hitoshi Isahara and
Bente Maegaard and
Joseph Mariani and
H{\'{e}}l{\`{e}}ne Mazo and
Asunci{\'{o}}n Moreno and
Jan Odijk and
Stelios Piperidis},
title = {{SMASH} Corpus: {A} Spontaneous Speech Corpus Recording Third-person
Audio Commentaries on Gameplay},
booktitle = {Proceedings of The 12th Language Resources and Evaluation Conference,
{LREC} 2020, Marseille, France, May 11-16, 2020},
pages = {6571--6577},
publisher = {European Language Resources Association},
year = {2020},
url = {https://aclanthology.org/2020.lrec-1.809/},
timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/lrec/SaitoTS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mmsp/IijimaKS20,
author = {Naoto Iijima and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Binaural Rendering From Distributed Microphone Signals Considering
Loudspeaker Distance in Measurements},
booktitle = {22nd {IEEE} International Workshop on Multimedia Signal Processing,
{MMSP} 2020, Tampere, Finland, September 21-24, 2020},
pages = {1--6},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/MMSP48831.2020.9287157},
doi = {10.1109/MMSP48831.2020.9287157},
timestamp = {Wed, 13 Jan 2021 17:58:36 +0100},
biburl = {https://dblp.org/rec/conf/mmsp/IijimaKS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2001-07044,
author = {Hiroki Tamaru and
Shinnosuke Takamichi and
Naoko Tanji and
Hiroshi Saruwatari},
title = {JVS-MuSiC: Japanese multispeaker singing-voice corpus},
journal = {CoRR},
volume = {abs/2001.07044},
year = {2020},
url = {https://arxiv.org/abs/2001.07044},
eprinttype = {arXiv},
eprint = {2001.07044},
timestamp = {Fri, 24 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2001-07044.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2001-10190,
author = {Tomohiko Nakamura and
Hiroshi Saruwatari},
title = {Time-Domain Audio Source Separation Based on Wave-U-Net Combined with
Discrete Wavelet Transform},
journal = {CoRR},
volume = {abs/2001.10190},
year = {2020},
url = {https://arxiv.org/abs/2001.10190},
eprinttype = {arXiv},
eprint = {2001.10190},
timestamp = {Thu, 30 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2001-10190.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-00579,
author = {Keigo Kamo and
Yuki Kubo and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Regularized Fast Multichannel Nonnegative Matrix Factorization with
ILRMA-based Prior Distribution of Joint-Diagonalization Process},
journal = {CoRR},
volume = {abs/2002.00579},
year = {2020},
url = {https://arxiv.org/abs/2002.00579},
eprinttype = {arXiv},
eprint = {2002.00579},
timestamp = {Mon, 10 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-00579.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-06778,
author = {Takaaki Saeki and
Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Lifter Training and Sub-band Modeling for Computationally Efficient
and High-Quality Voice Conversion Using Spectral Differentials},
journal = {CoRR},
volume = {abs/2002.06778},
year = {2020},
url = {https://arxiv.org/abs/2002.06778},
eprinttype = {arXiv},
eprint = {2002.06778},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-06778.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-08582,
author = {Tatsuki Kondo and
Kanta Fukushige and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari and
Rintaro Ikeshita and
Tomohiro Nakatani},
title = {Convergence-guaranteed Independent Positive Semidefinite Tensor Analysis
Based on Student's t Distribution},
journal = {CoRR},
volume = {abs/2002.08582},
year = {2020},
url = {https://arxiv.org/abs/2002.08582},
eprinttype = {arXiv},
eprint = {2002.08582},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-08582.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2004-10823,
author = {Tomoki Koriyama and
Hiroshi Saruwatari},
title = {Utterance-level Sequential Modeling For Deep Gaussian Process Based
Speech Synthesis Using Simple Recurrent Unit},
journal = {CoRR},
volume = {abs/2004.10823},
year = {2020},
url = {https://arxiv.org/abs/2004.10823},
eprinttype = {arXiv},
eprint = {2004.10823},
timestamp = {Wed, 29 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2004-10823.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-00416,
author = {Keigo Kamo and
Yuki Kubo and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Joint-Diagonalizability-Constrained Multichannel Nonnegative Matrix
Factorization Based on Multivariate Complex Sub-Gaussian Distribution},
journal = {CoRR},
volume = {abs/2007.00416},
year = {2020},
url = {https://arxiv.org/abs/2007.00416},
eprinttype = {arXiv},
eprint = {2007.00416},
timestamp = {Mon, 06 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-00416.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2008-02950,
author = {Kentaro Mitsui and
Tomoki Koriyama and
Hiroshi Saruwatari},
title = {Multi-speaker Text-to-speech Synthesis Using Deep Gaussian Processes},
journal = {CoRR},
volume = {abs/2008.02950},
year = {2020},
url = {https://arxiv.org/abs/2008.02950},
eprinttype = {arXiv},
eprint = {2008.02950},
timestamp = {Mon, 17 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2008-02950.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-01793,
author = {Shinnosuke Takamichi and
Mamoru Komachi and
Naoko Tanji and
Hiroshi Saruwatari},
title = {{JSSS:} free Japanese speech corpus for summarization and simplification},
journal = {CoRR},
volume = {abs/2010.01793},
year = {2020},
url = {https://arxiv.org/abs/2010.01793},
eprinttype = {arXiv},
eprint = {2010.01793},
timestamp = {Tue, 13 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-01793.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2012-12612,
author = {Takaaki Saeki and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Incremental Text-to-Speech Synthesis Using Pseudo Lookahead with Large
Pretrained Language Model},
journal = {CoRR},
volume = {abs/2012.12612},
year = {2020},
url = {https://arxiv.org/abs/2012.12612},
eprinttype = {arXiv},
eprint = {2012.12612},
timestamp = {Tue, 05 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2012-12612.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csl/SaitoTS19,
author = {Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Vocoder-free text-to-speech synthesis incorporating generative adversarial
networks using low-/multi-frequency {STFT} amplitude spectra},
journal = {Comput. Speech Lang.},
volume = {58},
pages = {347--363},
year = {2019},
url = {https://doi.org/10.1016/j.csl.2019.05.008},
doi = {10.1016/J.CSL.2019.05.008},
timestamp = {Thu, 20 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/csl/SaitoTS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/MogamiMTKSTKNK19,
author = {Shinichi Mogami and
Yoshiki Mitsui and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo and
Hiroaki Nakajima and
Hirokazu Kameoka},
title = {Independent Low-Rank Matrix Analysis Based on Generalized Kullback-Leibler
Divergence},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {102-A},
number = {2},
pages = {458--463},
year = {2019},
url = {https://doi.org/10.1587/transfun.E102.A.458},
doi = {10.1587/TRANSFUN.E102.A.458},
timestamp = {Mon, 18 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ieicet/MogamiMTKSTKNK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/SekizawaTS19,
author = {Daiki Sekizawa and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Prosody Correction Preserving Speaker Individuality for Chinese-Accented
Japanese HMM-Based Text-to-Speech Synthesis},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {102-D},
number = {6},
pages = {1218--1221},
year = {2019},
url = {https://doi.org/10.1587/transinf.2018EDL8264},
doi = {10.1587/TRANSINF.2018EDL8264},
timestamp = {Mon, 18 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ieicet/SekizawaTS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spl/NakajimaKTSO19,
author = {Hiroaki Nakajima and
Daichi Kitamura and
Norihiro Takamune and
Hiroshi Saruwatari and
Nobutaka Ono},
title = {Bilevel Optimization Using Stationary Point of Lower-Level Objective
Function for Discriminative Basis Learning in Nonnegative Matrix Factorization},
journal = {{IEEE} Signal Process. Lett.},
volume = {26},
number = {6},
pages = {818--822},
year = {2019},
url = {https://doi.org/10.1109/LSP.2019.2909079},
doi = {10.1109/LSP.2019.2909079},
timestamp = {Fri, 27 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/spl/NakajimaKTSO19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/MakishimaMTKSTS19,
author = {Naoki Makishima and
Shinichi Mogami and
Norihiro Takamune and
Daichi Kitamura and
Hayato Sumino and
Shinnosuke Takamichi and
Hiroshi Saruwatari and
Nobutaka Ono},
title = {Independent Deeply Learned Matrix Analysis for Determined Audio Source
Separation},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {27},
number = {10},
pages = {1601--1615},
year = {2019},
url = {https://doi.org/10.1109/TASLP.2019.2925450},
doi = {10.1109/TASLP.2019.2925450},
timestamp = {Fri, 27 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/MakishimaMTKSTS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/UenoKS19,
author = {Natsuki Ueno and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Three-Dimensional Sound Field Reproduction Based on Weighted Mode-Matching
Method},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {27},
number = {12},
pages = {1852--1867},
year = {2019},
url = {https://doi.org/10.1109/TASLP.2019.2934834},
doi = {10.1109/TASLP.2019.2934834},
timestamp = {Thu, 27 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/UenoKS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/KuboTKS19,
author = {Yuki Kubo and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari},
title = {Acceleration of rank-constrained spatial covariance matrix estimation
for blind speech extraction},
booktitle = {2019 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2019, Lanzhou, China, November
18-21, 2019},
pages = {332--338},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023281},
doi = {10.1109/APSIPAASC47483.2019.9023281},
timestamp = {Fri, 13 Mar 2020 10:17:58 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/KuboTKS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/MakishimaTSKTK19,
author = {Naoki Makishima and
Norihiro Takamune and
Hiroshi Saruwatari and
Daichi Kitamura and
Yu Takahashi and
Kazunobu Kondo},
title = {Robust Demixing Filter Update Algorithm Based on Microphone-wise Coordinate
Descent for Independent Deeply Learned Matrix Analysis},
booktitle = {2019 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2019, Lanzhou, China, November
18-21, 2019},
pages = {1868--1873},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023032},
doi = {10.1109/APSIPAASC47483.2019.9023032},
timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/MakishimaTSKTK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/UneKTKSM19,
author = {Masakazu Une and
Yuki Kubo and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari and
Shoji Makino},
title = {Evaluation of Multichannel Hearing Aid System by Rank-Constrained
Spatial Covariance Matrix Estimation},
booktitle = {2019 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2019, Lanzhou, China, November
18-21, 2019},
pages = {1874--1879},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023081},
doi = {10.1109/APSIPAASC47483.2019.9023081},
timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/UneKTKSM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/KuboTKS19,
author = {Yuki Kubo and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari},
title = {Efficient Full-Rank Spatial Covariance Estimation Using Independent
Low-Rank Matrix Analysis for Blind Source Separation},
booktitle = {27th European Signal Processing Conference, {EUSIPCO} 2019, {A} Coru{\~{n}}a,
Spain, September 2-6, 2019},
pages = {1--5},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.23919/EUSIPCO.2019.8903026},
doi = {10.23919/EUSIPCO.2019.8903026},
timestamp = {Mon, 25 Nov 2019 12:04:51 +0100},
biburl = {https://dblp.org/rec/conf/eusipco/KuboTKS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ItoKUS19,
author = {Hayato Ito and
Shoichi Koyama and
Natsuki Ueno and
Hiroshi Saruwatari},
title = {Feedforward Spatial Active Noise Control Based on Kernel Interpolation
of Sound Field},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {511--515},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8683067},
doi = {10.1109/ICASSP.2019.8683067},
timestamp = {Fri, 27 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/ItoKUS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TakidaKUS19,
author = {Yuhta Takida and
Shoichi Koyama and
Natsuki Ueno and
Hiroshi Saruwatari},
title = {Robust Gridless Sound Field Decomposition Based on Structured Reciprocity
Gap Functional in Spherical Harmonic Domain},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {581--585},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8683310},
doi = {10.1109/ICASSP.2019.8683310},
timestamp = {Fri, 27 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/TakidaKUS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TamaruSTKS19,
author = {Hiroki Tamaru and
Yuki Saito and
Shinnosuke Takamichi and
Tomoki Koriyama and
Hiroshi Saruwatari},
title = {Generative Moment Matching Network-based Random Modulation Post-filter
for DNN-based Singing Voice Synthesis and Neural Double-tracking},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {7070--7074},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8683476},
doi = {10.1109/ICASSP.2019.8683476},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/TamaruSTKS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uist/ArakawaTS19,
author = {Riku Arakawa and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
editor = {Fran{\c{c}}ois Guimbreti{\`{e}}re and
Michael S. Bernstein and
Katharina Reinecke},
title = {TransVoice: Real-Time Voice Conversion for Augmenting Near-Field Speech
Communication},
booktitle = {Adjunct Proceedings of the 32nd Annual {ACM} Symposium on User Interface
Software and Technology, {UIST} 2019, New Orleans, LA, USA, October
20-23, 2019},
pages = {33--35},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3332167.3357106},
doi = {10.1145/3332167.3357106},
timestamp = {Fri, 04 Feb 2022 08:27:42 +0100},
biburl = {https://dblp.org/rec/conf/uist/ArakawaTS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/waspaa/NakanishiUKS19,
author = {Masahiro Nakanishi and
Natsuki Ueno and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Two-Dimensional Sound Field Recording With Multiple Circular Microphone
Arrays Considering Multiple Scattering},
booktitle = {2019 {IEEE} Workshop on Applications of Signal Processing to Audio
and Acoustics, {WASPAA} 2019, New Paltz, NY, USA, October 20-23, 2019},
pages = {368--372},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/WASPAA.2019.8937208},
doi = {10.1109/WASPAA.2019.8937208},
timestamp = {Fri, 27 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/waspaa/NakanishiUKS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1902-03389,
author = {Hiroki Tamaru and
Yuki Saito and
Shinnosuke Takamichi and
Tomoki Koriyama and
Hiroshi Saruwatari},
title = {Generative Moment Matching Network-based Random Modulation Post-filter
for DNN-based Singing Voice Synthesis and Neural Double-tracking},
journal = {CoRR},
volume = {abs/1902.03389},
year = {2019},
url = {http://arxiv.org/abs/1902.03389},
eprinttype = {arXiv},
eprint = {1902.03389},
timestamp = {Tue, 21 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1902-03389.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-02482,
author = {Yuki Kubo and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari},
title = {Efficient Full-Rank Spatial Covariance Estimation Using Independent
Low-Rank Matrix Analysis for Blind Source Separation},
journal = {CoRR},
volume = {abs/1906.02482},
year = {2019},
url = {http://arxiv.org/abs/1906.02482},
eprinttype = {arXiv},
eprint = {1906.02482},
timestamp = {Thu, 13 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-02482.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-08294,
author = {Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {DNN-based Speaker Embedding Using Subjective Inter-speaker Similarity
for Multi-speaker Modeling in Speech Synthesis},
journal = {CoRR},
volume = {abs/1907.08294},
year = {2019},
url = {http://arxiv.org/abs/1907.08294},
eprinttype = {arXiv},
eprint = {1907.08294},
timestamp = {Tue, 23 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1907-08294.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-01454,
author = {Taiki Nakamura and
Yuki Saito and
Shinnosuke Takamichi and
Yusuke Ijima and
Hiroshi Saruwatari},
title = {{V2S} attack: building DNN-based voice conversion from automatic speaker
verification},
journal = {CoRR},
volume = {abs/1908.01454},
year = {2019},
url = {http://arxiv.org/abs/1908.01454},
eprinttype = {arXiv},
eprint = {1908.01454},
timestamp = {Fri, 09 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-01454.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-01964,
author = {Yuki Kubo and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari},
title = {Acceleration of rank-constrained spatial covariance matrix estimation
for blind speech extraction},
journal = {CoRR},
volume = {abs/1908.01964},
year = {2019},
url = {http://arxiv.org/abs/1908.01964},
eprinttype = {arXiv},
eprint = {1908.01964},
timestamp = {Fri, 09 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-01964.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-06248,
author = {Shinnosuke Takamichi and
Kentaro Mitsui and
Yuki Saito and
Tomoki Koriyama and
Naoko Tanji and
Hiroshi Saruwatari},
title = {{JVS} corpus: free Japanese multi-speaker voice corpus},
journal = {CoRR},
volume = {abs/1908.06248},
year = {2019},
url = {http://arxiv.org/abs/1908.06248},
eprinttype = {arXiv},
eprint = {1908.06248},
timestamp = {Mon, 26 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-06248.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-11391,
author = {Kazuki Fujii and
Yuki Saito and
Shinnosuke Takamichi and
Yukino Baba and
Hiroshi Saruwatari},
title = {HumanGAN: generative adversarial network with human-based discriminator
and its evaluation in speech perception modeling},
journal = {CoRR},
volume = {abs/1909.11391},
year = {2019},
url = {http://arxiv.org/abs/1909.11391},
eprinttype = {arXiv},
eprint = {1909.11391},
timestamp = {Fri, 27 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-11391.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ejasp/KitamuraMMTSOTK18,
author = {Daichi Kitamura and
Shinichi Mogami and
Yoshiki Mitsui and
Norihiro Takamune and
Hiroshi Saruwatari and
Nobutaka Ono and
Yu Takahashi and
Kazunobu Kondo},
title = {Generalized independent low-rank matrix analysis using heavy-tailed
distributions for blind source separation},
journal = {{EURASIP} J. Adv. Signal Process.},
volume = {2018},
pages = {28},
year = {2018},
url = {https://doi.org/10.1186/s13634-018-0549-5},
doi = {10.1186/S13634-018-0549-5},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ejasp/KitamuraMMTSOTK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spl/UenoKS18,
author = {Natsuki Ueno and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Sound Field Recording Using Distributed Microphones Based on Harmonic
Analysis of Infinite Order},
journal = {{IEEE} Signal Process. Lett.},
volume = {25},
number = {1},
pages = {135--139},
year = {2018},
url = {https://doi.org/10.1109/LSP.2017.2775242},
doi = {10.1109/LSP.2017.2775242},
timestamp = {Wed, 04 Jul 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/spl/UenoKS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/SaitoTS18,
author = {Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Statistical Parametric Speech Synthesis Incorporating Generative Adversarial
Networks},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {26},
number = {1},
pages = {84--96},
year = {2018},
url = {https://doi.org/10.1109/TASLP.2017.2761547},
doi = {10.1109/TASLP.2017.2761547},
timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/SaitoTS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsp/MurataKTS18,
author = {Naoki Murata and
Shoichi Koyama and
Norihiro Takamune and
Hiroshi Saruwatari},
title = {Sparse Representation Using Multidimensional Mixed-Norm Penalty With
Application to Sound Field Decomposition},
journal = {{IEEE} Trans. Signal Process.},
volume = {66},
number = {12},
pages = {3327--3338},
year = {2018},
url = {https://doi.org/10.1109/TSP.2018.2830318},
doi = {10.1109/TSP.2018.2830318},
timestamp = {Tue, 10 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tsp/MurataKTS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/UneSTKMS18,
author = {Masakazu Une and
Yuki Saito and
Shinnosuke Takamichi and
Daichi Kitamura and
Ryoichi Miyazaki and
Hiroshi Saruwatari},
title = {Generative approach using the noise generation models for DNN-based
speech synthesis trained from noisy speech},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2018, Honolulu, HI, USA, November
12-15, 2018},
pages = {340--344},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.23919/APSIPA.2018.8659691},
doi = {10.23919/APSIPA.2018.8659691},
timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/UneSTKMS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/AkiyamaTS18,
author = {Takanori Akiyama and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Prosody-aware subword embedding considering Japanese intonation systems
and its application to DNN-based multi-dialect speech synthesis},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2018, Honolulu, HI, USA, November
12-15, 2018},
pages = {659--664},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.23919/APSIPA.2018.8659465},
doi = {10.23919/APSIPA.2018.8659465},
timestamp = {Sat, 09 Mar 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/AkiyamaTS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/MogamiTKSTKNO18,
author = {Shinichi Mogami and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo and
Hiroaki Nakajima and
Nobutaka Ono},
title = {Independent Low-Rank Matrix Analysis Based on Time-Variant Sub-Gaussian
Source Model},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2018, Honolulu, HI, USA, November
12-15, 2018},
pages = {1684--1691},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.23919/APSIPA.2018.8659577},
doi = {10.23919/APSIPA.2018.8659577},
timestamp = {Fri, 27 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/MogamiTKSTKNO18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/MogamiSKTTSO18,
author = {Shinichi Mogami and
Hayato Sumino and
Daichi Kitamura and
Norihiro Takamune and
Shinnosuke Takamichi and
Hiroshi Saruwatari and
Nobutaka Ono},
title = {Independent Deeply Learned Matrix Analysis for Multichannel Audio
Source Separation},
booktitle = {26th European Signal Processing Conference, {EUSIPCO} 2018, Roma,
Italy, September 3-7, 2018},
pages = {1557--1561},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.23919/EUSIPCO.2018.8553246},
doi = {10.23919/EUSIPCO.2018.8553246},
timestamp = {Sat, 19 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/MogamiSKTTSO18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/TakidaKS18,
author = {Yuhta Takida and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Exterior and Interior Sound Field Separation Using Convex Optimization:
Comparison of Signal Models},
booktitle = {26th European Signal Processing Conference, {EUSIPCO} 2018, Roma,
Italy, September 3-7, 2018},
pages = {2549--2553},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.23919/EUSIPCO.2018.8552928},
doi = {10.23919/EUSIPCO.2018.8552928},
timestamp = {Fri, 27 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/eusipco/TakidaKS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/UenoKS18,
author = {Natsuki Ueno and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Sound Field Reproduction with Exterior Cancellation Using Analytical
Weighting of Harmonic Coefficients},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {466--470},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8462084},
doi = {10.1109/ICASSP.2018.8462084},
timestamp = {Fri, 27 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/UenoKS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MitsuiTKSTK18,
author = {Yoshiki Mitsui and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Vectorwise Coordinate Descent Algorithm for Spatially Regularized
Independent Low-Rank Matrix Analysis},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {746--750},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8462657},
doi = {10.1109/ICASSP.2018.8462657},
timestamp = {Tue, 18 Sep 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MitsuiTKSTK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaitoTS18,
author = {Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Text-to-Speech Synthesis Using {STFT} Spectra Based on Low-/Multi-Resolution
Generative Adversarial Networks},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {5299--5303},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8461714},
doi = {10.1109/ICASSP.2018.8461714},
timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SaitoTS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ieeesam/TakidaKUS18,
author = {Yuhta Takida and
Shoichi Koyama and
Natsuki Ueno and
Hiroshi Saruwatari},
title = {Gridless Sound Field Decomposition Based on Reciprocity Gap Functional
in Spherical Harmonic Domain},
booktitle = {10th {IEEE} Sensor Array and Multichannel Signal Processing Workshop,
{SAM} 2018, Sheffield, South Yorkshire, United Kingdom, July 8-11,
2018},
pages = {627--631},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/SAM.2018.8448736},
doi = {10.1109/SAM.2018.8448736},
timestamp = {Fri, 27 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ieeesam/TakidaKUS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwaenc/UenoKS18,
author = {Natsuki Ueno and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Kernel Ridge Regression with Constraint of Helmholtz Equation for
Sound Field Interpolation},
booktitle = {16th International Workshop on Acoustic Signal Enhancement, {IWAENC}
2018, Tokyo, Japan, September 17-20, 2018},
pages = {1--440},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/IWAENC.2018.8521334},
doi = {10.1109/IWAENC.2018.8521334},
timestamp = {Fri, 27 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iwaenc/UenoKS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwaenc/TakamichiSTKS18,
author = {Shinnosuke Takamichi and
Yuki Saito and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari},
title = {Phase Reconstruction from Amplitude Spectrograms Based on Von-Mises-Distribution
Deep Neural Network},
booktitle = {16th International Workshop on Acoustic Signal Enhancement, {IWAENC}
2018, Tokyo, Japan, September 17-20, 2018},
pages = {286--290},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/IWAENC.2018.8521313},
doi = {10.1109/IWAENC.2018.8521313},
timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iwaenc/TakamichiSTKS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/lrec/TakamichiS18,
author = {Shinnosuke Takamichi and
Hiroshi Saruwatari},
editor = {Nicoletta Calzolari and
Khalid Choukri and
Christopher Cieri and
Thierry Declerck and
Sara Goggi and
K{\^{o}}iti Hasida and
Hitoshi Isahara and
Bente Maegaard and
Joseph Mariani and
H{\'{e}}l{\`{e}}ne Mazo and
Asunci{\'{o}}n Moreno and
Jan Odijk and
Stelios Piperidis and
Takenobu Tokunaga},
title = {{CPJD} Corpus: Crowdsourced Parallel Speech Corpus of Japanese Dialects},
booktitle = {Proceedings of the Eleventh International Conference on Language Resources
and Evaluation, {LREC} 2018, Miyazaki, Japan, May 7-12, 2018},
publisher = {European Language Resources Association {(ELRA)}},
year = {2018},
url = {http://www.lrec-conf.org/proceedings/lrec2018/summaries/67.html},
timestamp = {Mon, 19 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/lrec/TakamichiS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-10307,
author = {Shinichi Mogami and
Hayato Sumino and
Daichi Kitamura and
Norihiro Takamune and
Shinnosuke Takamichi and
Hiroshi Saruwatari and
Nobutaka Ono},
title = {Independent Deeply Learned Matrix Analysis for Multichannel Audio
Source Separation},
journal = {CoRR},
volume = {abs/1806.10307},
year = {2018},
url = {http://arxiv.org/abs/1806.10307},
eprinttype = {arXiv},
eprint = {1806.10307},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-10307.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1807-03474,
author = {Shinnosuke Takamichi and
Yuki Saito and
Norihiro Takamune and
Daichi Kitamura and
Hiroshi Saruwatari},
title = {Phase reconstruction from amplitude spectrograms based on von-Mises-distribution
deep neural network},
journal = {CoRR},
volume = {abs/1807.03474},
year = {2018},
url = {http://arxiv.org/abs/1807.03474},
eprinttype = {arXiv},
eprint = {1807.03474},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1807-03474.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/SaitoTS17,
author = {Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Voice Conversion Using Input-to-Output Highway Networks},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {100-D},
number = {8},
pages = {1925--1928},
year = {2017},
url = {https://doi.org/10.1587/transinf.2017EDL8034},
doi = {10.1587/TRANSINF.2017EDL8034},
timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ieicet/SaitoTS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jrm/BandoSOMIKITMYM17,
author = {Yoshiaki Bando and
Hiroshi Saruwatari and
Nobutaka Ono and
Shoji Makino and
Katsutoshi Itoyama and
Daichi Kitamura and
Masaru Ishimura and
Moe Takakusaki and
Narumi Mae and
Kouei Yamaoka and
Yutaro Matsui and
Yuichi Ambe and
Masashi Konyo and
Satoshi Tadokoro and
Kazuyoshi Yoshii and
Hiroshi G. Okuno},
title = {Low Latency and High Quality Two-Stage Human-Voice-Enhancement System
for a Hose-Shaped Rescue Robot},
journal = {J. Robotics Mechatronics},
volume = {29},
number = {1},
pages = {198--212},
year = {2017},
url = {https://doi.org/10.20965/jrm.2017.p0198},
doi = {10.20965/JRM.2017.P0198},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jrm/BandoSOMIKITMYM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/MaeMMKOYS17,
author = {Narumi Mae and
Yoshiki Mitsui and
Shoji Makino and
Daichi Kitamura and
Nobutaka Ono and
Takeshi Yamada and
Hiroshi Saruwatari},
title = {Sound source localization using binaural difference for hose-shaped
rescue robot},
booktitle = {2017 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2017, Kuala Lumpur, Malaysia,
December 12-15, 2017},
pages = {1621--1627},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/APSIPA.2017.8282292},
doi = {10.1109/APSIPA.2017.8282292},
timestamp = {Sat, 19 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/MaeMMKOYS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/camsap/MitsuiKTSTK17,
author = {Yoshiki Mitsui and
Daichi Kitamura and
Norihiro Takamune and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Independent low-rank matrix analysis based on parametric majorization-equalization
algorithm},
booktitle = {2017 {IEEE} 7th International Workshop on Computational Advances in
Multi-Sensor Adaptive Processing, {CAMSAP} 2017, Cura{\c{c}}ao, The
Netherlands, December 10-13, 2017},
pages = {1--5},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/CAMSAP.2017.8313107},
doi = {10.1109/CAMSAP.2017.8313107},
timestamp = {Wed, 16 Oct 2019 14:14:56 +0200},
biburl = {https://dblp.org/rec/conf/camsap/MitsuiKTSTK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/KitamuraOS17,
author = {Daichi Kitamura and
Nobutaka Ono and
Hiroshi Saruwatari},
title = {Experimental analysis of optimal window length for independent low-rank
matrix analysis},
booktitle = {25th European Signal Processing Conference, {EUSIPCO} 2017, Kos, Greece,
August 28 - September 2, 2017},
pages = {1170--1174},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.23919/EUSIPCO.2017.8081392},
doi = {10.23919/EUSIPCO.2017.8081392},
timestamp = {Sat, 19 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/KitamuraOS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hscma/UenoKS17,
author = {Natsuki Ueno and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Listening-area-informed sound field reproduction with Gaussian prior
based on circular harmonic expansion},
booktitle = {Hands-free Speech Communications and Microphone Arrays, {HSCMA} 2017,
San Francisco, CA, USA, March 1-3, 2017},
pages = {196--200},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/HSCMA.2017.7895589},
doi = {10.1109/HSCMA.2017.7895589},
timestamp = {Wed, 16 Oct 2019 14:14:57 +0200},
biburl = {https://dblp.org/rec/conf/hscma/UenoKS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ica/MaeIMKOYS17,
author = {Narumi Mae and
Masaru Ishimura and
Shoji Makino and
Daichi Kitamura and
Nobutaka Ono and
Takeshi Yamada and
Hiroshi Saruwatari},
editor = {Petr Tichavsk{\'{y}} and
Massoud Babaie{-}Zadeh and
Olivier J. J. Michel and
Nad{\`{e}}ge Thirion{-}Moreau},
title = {Ego Noise Reduction for Hose-Shaped Rescue Robot Combining Independent
Low-Rank Matrix Analysis and Multichannel Noise Cancellation},
booktitle = {Latent Variable Analysis and Signal Separation - 13th International
Conference, {LVA/ICA} 2017, Grenoble, France, February 21-23, 2017,
Proceedings},
series = {Lecture Notes in Computer Science},
volume = {10169},
pages = {141--151},
year = {2017},
url = {https://doi.org/10.1007/978-3-319-53547-0\_14},
doi = {10.1007/978-3-319-53547-0\_14},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ica/MaeIMKOYS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MitsuiKTOS17,
author = {Yoshiki Mitsui and
Daichi Kitamura and
Shinnosuke Takamichi and
Nobutaka Ono and
Hiroshi Saruwatari},
title = {Blind source separation based on independent low-rank matrix analysis
with sparse regularization for time-series activity},
booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
pages = {21--25},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ICASSP.2017.7951790},
doi = {10.1109/ICASSP.2017.7951790},
timestamp = {Sat, 19 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MitsuiKTOS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/UenoKS17,
author = {Natsuki Ueno and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Listening-area-informed sound field reproduction based on circular
harmonic expansion},
booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
pages = {111--115},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ICASSP.2017.7952128},
doi = {10.1109/ICASSP.2017.7952128},
timestamp = {Sat, 16 Sep 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/UenoKS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MurataKTS17,
author = {Naoki Murata and
Shoichi Koyama and
Norihiro Takamune and
Hiroshi Saruwatari},
title = {Spatio-temporal sparse sound field decomposition considering acoustic
source signal characteristics},
booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
pages = {441--445},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ICASSP.2017.7952194},
doi = {10.1109/ICASSP.2017.7952194},
timestamp = {Sat, 16 Sep 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MurataKTS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaitoTS17,
author = {Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Training algorithm to deceive Anti-Spoofing Verification for DNN-based
speech synthesis},
booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
pages = {4900--4904},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ICASSP.2017.7953088},
doi = {10.1109/ICASSP.2017.7953088},
timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SaitoTS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MiyoshiSTS17,
author = {Hiroyuki Miyoshi and
Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
editor = {Francisco Lacerda},
title = {Voice Conversion Using Sequence-to-Sequence Learning of Context Posterior
Probabilities},
booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech
Communication Association, Stockholm, Sweden, August 20-24, 2017},
pages = {1268--1272},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-247},
doi = {10.21437/INTERSPEECH.2017-247},
timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MiyoshiSTS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TakamichiKS17,
author = {Shinnosuke Takamichi and
Tomoki Koriyama and
Hiroshi Saruwatari},
editor = {Francisco Lacerda},
title = {Sampling-Based Speech Parameter Generation Using Moment-Matching Networks},
booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech
Communication Association, Stockholm, Sweden, August 20-24, 2017},
pages = {3961--3965},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-362},
doi = {10.21437/INTERSPEECH.2017-362},
timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/TakamichiKS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mlsp/MogamiKMTSO17,
author = {Shinichi Mogami and
Daichi Kitamura and
Yoshiki Mitsui and
Norihiro Takamune and
Hiroshi Saruwatari and
Nobutaka Ono},
editor = {Naonori Ueda and
Shinji Watanabe and
Tomoko Matsui and
Jen{-}Tzung Chien and
Jan Larsen},
title = {Independent low-rank matrix analysis based on complex student's t-distribution
for blind audio source separation},
booktitle = {27th {IEEE} International Workshop on Machine Learning for Signal
Processing, {MLSP} 2017, Tokyo, Japan, September 25-28, 2017},
pages = {1--6},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/MLSP.2017.8168129},
doi = {10.1109/MLSP.2017.8168129},
timestamp = {Tue, 30 Jun 2020 10:25:30 +0200},
biburl = {https://dblp.org/rec/conf/mlsp/MogamiKMTSO17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MiyoshiSTS17,
author = {Hiroyuki Miyoshi and
Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Voice Conversion Using Sequence-to-Sequence Learning of Context Posterior
Probabilities},
journal = {CoRR},
volume = {abs/1704.02360},
year = {2017},
url = {http://arxiv.org/abs/1704.02360},
eprinttype = {arXiv},
eprint = {1704.02360},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MiyoshiSTS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TakamichiKS17,
author = {Shinnosuke Takamichi and
Tomoki Koriyama and
Hiroshi Saruwatari},
title = {Sampling-based speech parameter generation using moment-matching networks},
journal = {CoRR},
volume = {abs/1704.03626},
year = {2017},
url = {http://arxiv.org/abs/1704.03626},
eprinttype = {arXiv},
eprint = {1704.03626},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/TakamichiKS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1708-04795,
author = {Shinichi Mogami and
Daichi Kitamura and
Yoshiki Mitsui and
Norihiro Takamune and
Hiroshi Saruwatari and
Nobutaka Ono},
title = {Independent Low-Rank Matrix Analysis Based on Complex Student's t-Distribution
for Blind Audio Source Separation},
journal = {CoRR},
volume = {abs/1708.04795},
year = {2017},
url = {http://arxiv.org/abs/1708.04795},
eprinttype = {arXiv},
eprint = {1708.04795},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1708-04795.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1709-08041,
author = {Yuki Saito and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {Statistical Parametric Speech Synthesis Incorporating Generative Adversarial
Networks},
journal = {CoRR},
volume = {abs/1709.08041},
year = {2017},
url = {http://arxiv.org/abs/1709.08041},
eprinttype = {arXiv},
eprint = {1709.08041},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1709-08041.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1710-01589,
author = {Yoshiki Mitsui and
Daichi Kitamura and
Norihiro Takamune and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Independent Low-Rank Matrix Analysis Based on Parametric Majorization-Equalization
Algorithm},
journal = {CoRR},
volume = {abs/1710.01589},
year = {2017},
url = {http://arxiv.org/abs/1710.01589},
eprinttype = {arXiv},
eprint = {1710.01589},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1710-01589.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1711-00354,
author = {Ryosuke Sonobe and
Shinnosuke Takamichi and
Hiroshi Saruwatari},
title = {{JSUT} corpus: free large-scale Japanese speech corpus for end-to-end
speech synthesis},
journal = {CoRR},
volume = {abs/1711.00354},
year = {2017},
url = {http://arxiv.org/abs/1711.00354},
eprinttype = {arXiv},
eprint = {1711.00354},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1711-00354.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/KitamuraOSKS16,
author = {Daichi Kitamura and
Nobutaka Ono and
Hiroshi Sawada and
Hirokazu Kameoka and
Hiroshi Saruwatari},
title = {Determined Blind Source Separation Unifying Independent Vector Analysis
and Nonnegative Matrix Factorization},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {24},
number = {9},
pages = {1626--1641},
year = {2016},
url = {https://doi.org/10.1109/TASLP.2016.2577880},
doi = {10.1109/TASLP.2016.2577880},
timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/KitamuraOSKS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/NakajimaKTKSTK16,
author = {Hiroaki Nakajima and
Daichi Kitamura and
Norihiro Takamune and
Shoichi Koyama and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Audio signal separation using supervised {NMF} with time-variant all-pole-model-based
basis deformation},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2016, Jeju, South Korea, December
13-16, 2016},
pages = {1--7},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/APSIPA.2016.7820763},
doi = {10.1109/APSIPA.2016.7820763},
timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/NakajimaKTKSTK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/NakajimaKTKSOTK16,
author = {Hiroaki Nakajima and
Daichi Kitamura and
Norihiro Takamune and
Shoichi Koyama and
Hiroshi Saruwatari and
Nobutaka Ono and
Yu Takahashi and
Kazunobu Kondo},
title = {Music signal separation using supervised {NMF} with all-pole-model-based
discriminative basis deformation},
booktitle = {24th European Signal Processing Conference, {EUSIPCO} 2016, Budapest,
Hungary, August 29 - September 2, 2016},
pages = {1143--1147},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/EUSIPCO.2016.7760427},
doi = {10.1109/EUSIPCO.2016.7760427},
timestamp = {Sat, 19 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/NakajimaKTKSOTK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/MurataKKANKS16,
author = {Naoki Murata and
Hirokazu Kameoka and
Keisuke Kinoshita and
Shoko Araki and
Tomohiro Nakatani and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Reverberation-robust underdetermined source separation with non-negative
tensor double deconvolution},
booktitle = {24th European Signal Processing Conference, {EUSIPCO} 2016, Budapest,
Hungary, August 29 - September 2, 2016},
pages = {1648--1652},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/EUSIPCO.2016.7760528},
doi = {10.1109/EUSIPCO.2016.7760528},
timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/eusipco/MurataKKANKS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MitsufujiKS16,
author = {Yuki Mitsufuji and
Shoichi Koyama and
Hiroshi Saruwatari},
title = {Multichannel blind source separation based on non-negative tensor
factorization in wavenumber domain},
booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
pages = {56--60},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/ICASSP.2016.7471636},
doi = {10.1109/ICASSP.2016.7471636},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MitsufujiKS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MurataKKTS16,
author = {Naoki Murata and
Shoichi Koyama and
Hirokazu Kameoka and
Norihiro Takamune and
Hiroshi Saruwatari},
title = {Sparse sound field decomposition with multichannel extension of complex
{NMF}},
booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
pages = {345--349},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/ICASSP.2016.7471694},
doi = {10.1109/ICASSP.2016.7471694},
timestamp = {Sat, 16 Sep 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MurataKKTS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KoyamaS16,
author = {Shoichi Koyama and
Hiroshi Saruwatari},
title = {Sound field decomposition in reverberant environment using sparse
and low-rank signal models},
booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
pages = {395--399},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/ICASSP.2016.7471704},
doi = {10.1109/ICASSP.2016.7471704},
timestamp = {Sat, 16 Sep 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KoyamaS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiKHS16,
author = {Li Li and
Hirokazu Kameoka and
Takuya Higuchi and
Hiroshi Saruwatari},
editor = {Nelson Morgan},
title = {Semi-Supervised Joint Enhancement of Spectral and Cepstral Sequences
of Noisy Speech},
booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech
Communication Association, San Francisco, CA, USA, September 8-12,
2016},
pages = {3753--3757},
publisher = {{ISCA}},
year = {2016},
url = {https://doi.org/10.21437/Interspeech.2016-1286},
doi = {10.21437/INTERSPEECH.2016-1286},
timestamp = {Mon, 26 Jun 2023 16:43:56 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiKHS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwaenc/IshimuraMYOS16,
author = {Masaru Ishimura and
Shoji Makino and
Takeshi Yamada and
Nobutaka Ono and
Hiroshi Saruwatari},
title = {Noise reduction using independent vector analysis and noise cancellation
for a hose-shaped rescue robot},
booktitle = {{IEEE} International Workshop on Acoustic Signal Enhancement, {IWAENC}
2016, Xi'an, China, September 13-16, 2016},
pages = {1--5},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/IWAENC.2016.7602912},
doi = {10.1109/IWAENC.2016.7602912},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iwaenc/IshimuraMYOS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwaenc/KitamuraOSTK16,
author = {Daichi Kitamura and
Nobutaka Ono and
Hiroshi Saruwatari and
Yu Takahashi and
Kazunobu Kondo},
title = {Discriminative and reconstructive basis training for audio source
separation with semi-supervised nonnegative matrix factorization},
booktitle = {{IEEE} International Workshop on Acoustic Signal Enhancement, {IWAENC}
2016, Xi'an, China, September 13-16, 2016},
pages = {1--5},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/IWAENC.2016.7602901},
doi = {10.1109/IWAENC.2016.7602901},
timestamp = {Sat, 19 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iwaenc/KitamuraOSTK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwaenc/TakakusakiKOYMS16,
author = {Moe Takakusaki and
Daichi Kitamura and
Nobutaka Ono and
Takeshi Yamada and
Shoji Makino and
Hiroshi Saruwatari},
title = {Ego-noise reduction for a hose-shaped rescue robot using determined
rank-1 multichannel nonnegative matrix factorization},
booktitle = {{IEEE} International Workshop on Acoustic Signal Enhancement, {IWAENC}
2016, Xi'an, China, September 13-16, 2016},
pages = {1--4},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/IWAENC.2016.7602914},
doi = {10.1109/IWAENC.2016.7602914},
timestamp = {Sat, 19 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iwaenc/TakakusakiKOYMS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/KitamuraSKTKN15,
author = {Daichi Kitamura and
Hiroshi Saruwatari and
Hirokazu Kameoka and
Yu Takahashi and
Kazunobu Kondo and
Satoshi Nakamura},
title = {Multichannel Signal Separation Combining Directional Clustering and
Nonnegative Matrix Factorization with Spectrogram Restoration},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {23},
number = {4},
pages = {654--669},
year = {2015},
url = {https://doi.org/10.1109/TASLP.2015.2401425},
doi = {10.1109/TASLP.2015.2401425},
timestamp = {Tue, 16 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/KitamuraSKTKN15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/KoyamaMMS15,
author = {Shoichi Koyama and
Atsushi Matsubayashi and
Naoki Murata and
Hiroshi Saruwatari},
title = {Sparse sound field decomposition using group sparse Bayesian learning},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2015, Hong Kong, December 16-19, 2015},
pages = {850--855},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/APSIPA.2015.7415391},
doi = {10.1109/APSIPA.2015.7415391},
timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/KoyamaMMS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/camsap/MurataKTS15,
author = {Naoki Murata and
Shoichi Koyama and
Norihiro Takamune and
Hiroshi Saruwatari},
title = {Sparse sound field decomposition with parametric dictionary learning
for super-resolution recording and reproduction},
booktitle = {6th {IEEE} International Workshop on Computational Advances in Multi-Sensor
Adaptive Processing, {CAMSAP} 2015, Cancun, Mexico, December 13-16,
2015},
pages = {69--72},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/CAMSAP.2015.7383738},
doi = {10.1109/CAMSAP.2015.7383738},
timestamp = {Wed, 16 Oct 2019 14:14:56 +0200},
biburl = {https://dblp.org/rec/conf/camsap/MurataKTS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/KitamuraOSKS15,
author = {Daichi Kitamura and
Nobutaka Ono and
Hiroshi Sawada and
Hirokazu Kameoka and
Hiroshi Saruwatari},
title = {Relaxation of rank-1 spatial constraint in overdetermined blind source
separation},
booktitle = {23rd European Signal Processing Conference, {EUSIPCO} 2015, Nice,
France, August 31 - September 4, 2015},
pages = {1261--1265},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/EUSIPCO.2015.7362586},
doi = {10.1109/EUSIPCO.2015.7362586},
timestamp = {Sat, 19 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/KitamuraOSKS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KitamuraOSKS15,
author = {Daichi Kitamura and
Nobutaka Ono and
Hiroshi Sawada and
Hirokazu Kameoka and
Hiroshi Saruwatari},
title = {Efficient multichannel nonnegative matrix factorization exploiting
rank-1 spatial model},
booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia,
April 19-24, 2015},
pages = {276--280},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ICASSP.2015.7177975},
doi = {10.1109/ICASSP.2015.7177975},
timestamp = {Sat, 19 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KitamuraOSKS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MurotaKKSN15,
author = {Yuki Murota and
Daichi Kitamura and
Shoichi Koyama and
Hiroshi Saruwatari and
Satoshi Nakamura},
title = {Statistical modeling of binaural signal and its application to binaural
source separation},
booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia,
April 19-24, 2015},
pages = {494--498},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ICASSP.2015.7178018},
doi = {10.1109/ICASSP.2015.7178018},
timestamp = {Sat, 16 Sep 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MurotaKKSN15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KoyamaMS15,
author = {Shoichi Koyama and
Naoki Murata and
Hiroshi Saruwatari},
title = {Structured sparse signal models and decomposition algorithm for super-resolution
in sound field recording and reproduction},
booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia,
April 19-24, 2015},
pages = {619--623},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ICASSP.2015.7178043},
doi = {10.1109/ICASSP.2015.7178043},
timestamp = {Sat, 16 Sep 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KoyamaMS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdsp/Saruwatari15,
author = {Hiroshi Saruwatari},
title = {Statistical-model-based speech enhancement with musical-noise-free
properties},
booktitle = {2015 {IEEE} International Conference on Digital Signal Processing,
{DSP} 2015, Singapore, July 21-24, 2015},
pages = {1201--1205},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ICDSP.2015.7252070},
doi = {10.1109/ICDSP.2015.7252070},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/icdsp/Saruwatari15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/waspaa/KoyamaIS15,
author = {Shoichi Koyama and
Koichiro Ito and
Hiroshi Saruwatari},
title = {Source-location-informed sound field recording and reproduction with
spherical arrays},
booktitle = {2015 {IEEE} Workshop on Applications of Signal Processing to Audio
and Acoustics, {WASPAA} 2015, New Paltz, NY, USA, October 18-21, 2015},
pages = {1--5},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/WASPAA.2015.7336914},
doi = {10.1109/WASPAA.2015.7336914},
timestamp = {Wed, 16 Oct 2019 14:14:57 +0200},
biburl = {https://dblp.org/rec/conf/waspaa/KoyamaIS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/KitamuraSYSTK14,
author = {Daichi Kitamura and
Hiroshi Saruwatari and
Kosuke Yagi and
Kiyohiro Shikano and
Yu Takahashi and
Kazunobu Kondo},
title = {Music Signal Separation Based on Supervised Nonnegative Matrix Factorization
with Orthogonality and Maximum-Divergence Penalties},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {97-A},
number = {5},
pages = {1113--1118},
year = {2014},
url = {https://doi.org/10.1587/transfun.E97.A.1113},
doi = {10.1587/TRANSFUN.E97.A.1113},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ieicet/KitamuraSYSTK14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sigpro/MiyazakiSNSKBB14,
author = {Ryoichi Miyazaki and
Hiroshi Saruwatari and
Satoshi Nakamura and
Kiyohiro Shikano and
Kazunobu Kondo and
Jonathan Blanchette and
Martin Bouchard},
title = {Musical-noise-free blind speech extraction integrating microphone
array and iterative spectral subtraction},
journal = {Signal Process.},
volume = {102},
pages = {226--239},
year = {2014},
url = {https://doi.org/10.1016/j.sigpro.2014.03.010},
doi = {10.1016/J.SIGPRO.2014.03.010},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/sigpro/MiyazakiSNSKBB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/DoiTNSS14,
author = {Hironori Doi and
Tomoki Toda and
Keigo Nakamura and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Alaryngeal Speech Enhancement Based on One-to-Many Eigenvoice Conversion},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {22},
number = {1},
pages = {172--183},
year = {2014},
url = {https://doi.org/10.1109/TASLP.2013.2286917},
doi = {10.1109/TASLP.2013.2286917},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/DoiTNSS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/KitamuraSNTKK14,
author = {Daichi Kitamura and
Hiroshi Saruwatari and
Satoshi Nakamura and
Yu Takahashi and
Kazunobu Kondo and
Hirokazu Kameoka},
title = {Hybrid multichannel signal separation using supervised nonnegative
matrix factorization with spectrogram restoration},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2014, Chiang Mai, Thailand, December
9-12, 2014},
pages = {1--10},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/APSIPA.2014.7041664},
doi = {10.1109/APSIPA.2014.7041664},
timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/KitamuraSNTKK14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hscma/KitamuraSNTKK14,
author = {Daichi Kitamura and
Hiroshi Saruwatari and
Satoshi Nakamura and
Yu Takahashi and
Kazunobu Kondo and
Hirokazu Kameoka},
title = {Divergence optimization in nonnegative matrix factorization with spectrogram
restoration for multichannel signal separation},
booktitle = {4th Joint Workshop on Hands-free Speech Communication and Microphone
Arrays, {HSCMA} 2014, Villers-les-Nancy, France, May 12-14, 2014},
pages = {92--96},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/HSCMA.2014.6843258},
doi = {10.1109/HSCMA.2014.6843258},
timestamp = {Wed, 16 Oct 2019 14:14:57 +0200},
biburl = {https://dblp.org/rec/conf/hscma/KitamuraSNTKK14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hscma/NakaiSMNK14,
author = {Shunsuke Nakai and
Hiroshi Saruwatari and
Ryoichi Miyazaki and
Satoshi Nakamura and
Kazunobu Kondo},
title = {Theoretical analysis of biased {MMSE} short-time spectral amplitude
estimator and its extension to musical-noise-free speech enhancement},
booktitle = {4th Joint Workshop on Hands-free Speech Communication and Microphone
Arrays, {HSCMA} 2014, Villers-les-Nancy, France, May 12-14, 2014},
pages = {122--126},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/HSCMA.2014.6843264},
doi = {10.1109/HSCMA.2014.6843264},
timestamp = {Thu, 24 Aug 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/hscma/NakaiSMNK14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hscma/AprilyantiSNT14,
author = {Fine Dwinita Aprilyanti and
Hiroshi Saruwatari and
Satoshi Nakamura and
Tomoya Takatani},
title = {Optimized joint noise suppression and dereverberation based on blind
signal extraction for hands-free speech recognition system},
booktitle = {4th Joint Workshop on Hands-free Speech Communication and Microphone
Arrays, {HSCMA} 2014, Villers-les-Nancy, France, May 12-14, 2014},
pages = {182--186},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/HSCMA.2014.6843276},
doi = {10.1109/HSCMA.2014.6843276},
timestamp = {Thu, 24 Aug 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/hscma/AprilyantiSNT14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MurotaKNSNTK14,
author = {Yuki Murota and
Daichi Kitamura and
Shunsuke Nakai and
Hiroshi Saruwatari and
Satoshi Nakamura and
Yu Takahashi and
Kazunobu Kondo},
title = {Music signal separation based on Bayesian spectral amplitude estimator
with automatic target prior adaptation},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2014, Florence, Italy, May 4-9, 2014},
pages = {7490--7494},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICASSP.2014.6855056},
doi = {10.1109/ICASSP.2014.6855056},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MurotaKNSNTK14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sigpro/MustiereBNPTS13,
author = {Fr{\'{e}}d{\'{e}}ric Musti{\`{e}}re and
Martin Bouchard and
Hossein Najaf{-}Zadeh and
Ramin Pichevar and
Louis Thibault and
Hiroshi Saruwatari},
title = {Design of multichannel frequency domain statistical-based enhancement
systems preserving spatial cues via spectral distances minimization},
journal = {Signal Process.},
volume = {93},
number = {1},
pages = {321--325},
year = {2013},
url = {https://doi.org/10.1016/j.sigpro.2012.06.024},
doi = {10.1016/J.SIGPRO.2012.06.024},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/sigpro/MustiereBNPTS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/AprilyantiSSNT13,
author = {Fine Dwinita Aprilyanti and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Satoshi Nakamura and
Tomoya Takatani},
title = {Semi-blind algorithm for joint noise suppression and dereverberation
based on higher-order statistics and acoustic model likelihood},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2013, Kaohsiung, Taiwan, October 29
- November 1, 2013},
pages = {1--6},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/APSIPA.2013.6694161},
doi = {10.1109/APSIPA.2013.6694161},
timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/AprilyantiSSNT13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/MiyazakiSNSKBB13,
author = {Ryoichi Miyazaki and
Hiroshi Saruwatari and
Satoshi Nakamura and
Kiyohiro Shikano and
Kazunobu Kondo and
Jonathan Blanchette and
Martin Bouchard},
title = {Toward musical-noise-free blind speech extraction: Concept and its
applications},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2013, Kaohsiung, Taiwan, October 29
- November 1, 2013},
pages = {1--10},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/APSIPA.2013.6694291},
doi = {10.1109/APSIPA.2013.6694291},
timestamp = {Thu, 26 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/MiyazakiSNSKBB13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdsp/KitamuraSISKT13,
author = {Daichi Kitamura and
Hiroshi Saruwatari and
Yusuke Iwao and
Kiyohiro Shikano and
Kazunobu Kondo and
Yu Takahashi},
title = {Superresolution-based stereo signal separation via supervised nonnegative
matrix factorization},
booktitle = {18th International Conference on Digital Signal Processing, {DSP}
2013, Fira, Santorini, Greece, July 1-3, 2013},
pages = {1--6},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICDSP.2013.6622684},
doi = {10.1109/ICDSP.2013.6622684},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/icdsp/KitamuraSISKT13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdsp/KitamuraSSKT13,
author = {Daichi Kitamura and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Kazunobu Kondo and
Yu Takahashi},
title = {Music signal separation by supervised nonnegative matrix factorization
with basis deformation},
booktitle = {18th International Conference on Digital Signal Processing, {DSP}
2013, Fira, Santorini, Greece, July 1-3, 2013},
pages = {1--6},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICDSP.2013.6622812},
doi = {10.1109/ICDSP.2013.6622812},
timestamp = {Wed, 24 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icdsp/KitamuraSSKT13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaruwatariKMSK13,
author = {Hiroshi Saruwatari and
Suzumi Kanehara and
Ryoichi Miyazaki and
Kiyohiro Shikano and
Kazunobu Kondo},
editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and
Christophe Cerisara and
C{\'{e}}cile Fougeron and
Guillaume Gravier and
Lori Lamel and
Fran{\c{c}}ois Pellegrino and
Pascal Perrier},
title = {Musical noise analysis for Bayesian minimum mean-square error speech
amplitude estimators based on higher-order statistics},
booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech
Communication Association, Lyon, France, August 25-29, 2013},
pages = {441--445},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-131},
doi = {10.21437/INTERSPEECH.2013-131},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaruwatariKMSK13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ispacs/SaruwatariM13,
author = {Hiroshi Saruwatari and
Ryoichi Miyazaki},
title = {Information-geometric optimization for nonlinear noise reduction systems},
booktitle = {International Symposium on Intelligent Signal Processing and Communication
Systems, {ISPACS} 2013, Naha-shi, Japan, November 12-15, 2013},
pages = {192--197},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ISPACS.2013.6704545},
doi = {10.1109/ISPACS.2013.6704545},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/ispacs/SaruwatariM13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isspit/KitamuraSYSTK13,
author = {Daichi Kitamura and
Hiroshi Saruwatari and
Kosuke Yagi and
Kiyohiro Shikano and
Yu Takahashi and
Kazunobu Kondo},
title = {Robust music signal separation based on supervised nonnegative matrix
factorization with prevention of basis sharing},
booktitle = {{IEEE} International Symposium on Signal Processing and Information
Technology, Athens, Greece, December 12-15, 2013},
pages = {392--397},
publisher = {{IEEE} Computer Society},
year = {2013},
url = {https://doi.org/10.1109/ISSPIT.2013.6781913},
doi = {10.1109/ISSPIT.2013.6781913},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/isspit/KitamuraSYSTK13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/MiyazakiSS12,
author = {Ryoichi Miyazaki and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Theoretical Analysis of Amounts of Musical Noise and Speech Distortion
in Structure-Generalized Parametric Blind Spatial Subtraction Array},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {95-A},
number = {2},
pages = {586--590},
year = {2012},
url = {https://doi.org/10.1587/transfun.E95.A.586},
doi = {10.1587/TRANSFUN.E95.A.586},
timestamp = {Sat, 11 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/MiyazakiSS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/WakisakaSST12,
author = {Ryo Wakisaka and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Tomoya Takatani},
title = {Speech Prior Estimation for Generalized Minimum Mean-Square Error
Short-Time Spectral Amplitude Estimator},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {95-A},
number = {2},
pages = {591--595},
year = {2012},
url = {https://doi.org/10.1587/transfun.E95.A.591},
doi = {10.1587/TRANSFUN.E95.A.591},
timestamp = {Sat, 11 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/WakisakaSST12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/NakamuraTSS12,
author = {Keigo Nakamura and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Speaking-aid systems using GMM-based voice conversion for electrolaryngeal
speech},
journal = {Speech Commun.},
volume = {54},
number = {1},
pages = {134--146},
year = {2012},
url = {https://doi.org/10.1016/j.specom.2011.07.007},
doi = {10.1016/J.SPECOM.2011.07.007},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/speech/NakamuraTSS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/MiyazakiSITSK12,
author = {Ryoichi Miyazaki and
Hiroshi Saruwatari and
Takayuki Inoue and
Yu Takahashi and
Kiyohiro Shikano and
Kazunobu Kondo},
title = {Musical-Noise-Free Speech Enhancement Based on Optimized Iterative
Spectral Subtraction},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {20},
number = {7},
pages = {2080--2094},
year = {2012},
url = {https://doi.org/10.1109/TASL.2012.2196513},
doi = {10.1109/TASL.2012.2196513},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/MiyazakiSITSK12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/AprilyantiSST12,
author = {Fine Dwinita Aprilyanti and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Tomoya Takatani},
title = {Optimization scheme of joint noise suppression and dereverberation
based on higher-order statistics},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2012, Hollywood, CA, USA, December
3-6, 2012},
pages = {1--6},
publisher = {{IEEE}},
year = {2012},
url = {https://ieeexplore.ieee.org/document/6411822/},
timestamp = {Sun, 08 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/AprilyantiSST12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/KaneharaSMSK12,
author = {Suzumi Kanehara and
Hiroshi Saruwatari and
Ryoichi Miyazaki and
Kiyohiro Shikano and
Kazunobu Kondo},
title = {Comparative study on various noise reduction methods with decision-directed
a priori {SNR} estimator via higher-order statistics},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2012, Hollywood, CA, USA, December
3-6, 2012},
pages = {1--6},
publisher = {{IEEE}},
year = {2012},
url = {https://ieeexplore.ieee.org/document/6411806/},
timestamp = {Sun, 08 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/KaneharaSMSK12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/NishimuraKSS12,
author = {Kazuma Nishimura and
Hiromichi Kawanami and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Response generation based on statistical machine translation for speech-oriented
guidance system},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2012, Hollywood, CA, USA, December
3-6, 2012},
pages = {1--4},
publisher = {{IEEE}},
year = {2012},
url = {https://ieeexplore.ieee.org/document/6411808/},
timestamp = {Sun, 08 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/NishimuraKSS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/OnumaKSS12,
author = {Yuji Onuma and
Noriyoshi Kamado and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Real-time semi-blind speech extraction with speaker direction tracking
on Kinect},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2012, Hollywood, CA, USA, December
3-6, 2012},
pages = {1--6},
publisher = {{IEEE}},
year = {2012},
url = {https://ieeexplore.ieee.org/document/6411817/},
timestamp = {Sun, 08 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/OnumaKSS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/TakahashiMSK12,
author = {Yu Takahashi and
Ryoichi Miyazaki and
Hiroshi Saruwatari and
Kazunobu Kondo},
title = {Theoretical analysis of musical noise in nonlinear noise reduction
based on higher-order statistics},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2012, Hollywood, CA, USA, December
3-6, 2012},
pages = {1--10},
publisher = {{IEEE}},
year = {2012},
url = {https://ieeexplore.ieee.org/document/6411877/},
timestamp = {Sun, 08 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/TakahashiMSK12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/SaruwatariWSMTNB12,
author = {Hiroshi Saruwatari and
Ryo Wakisaka and
Kiyohiro Shikano and
Fr{\'{e}}d{\'{e}}ric Musti{\`{e}}re and
Louis Thibault and
Hossein Najaf{-}Zadeh and
Martin Bouchard},
title = {Sound-localization-preserved binaural {MMSE} {STSA} estimator with
explicit and implicit binaural cues},
booktitle = {Proceedings of the 20th European Signal Processing Conference, {EUSIPCO}
2012, Bucharest, Romania, August 27-31, 2012},
pages = {310--314},
publisher = {{IEEE}},
year = {2012},
url = {https://ieeexplore.ieee.org/document/6334345/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/SaruwatariWSMTNB12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/KamadoHSS12,
author = {Noriyoshi Kamado and
Masayuki Hirata and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Object-based stereo up-mixer for wave field synthesis based on spatial
information clustering},
booktitle = {Proceedings of the 20th European Signal Processing Conference, {EUSIPCO}
2012, Bucharest, Romania, August 27-31, 2012},
pages = {594--598},
publisher = {{IEEE}},
year = {2012},
url = {https://ieeexplore.ieee.org/document/6334180/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/KamadoHSS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WakisakaSST12,
author = {Ryo Wakisaka and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Tomoya Takatani},
title = {Speech kurtosis estimation from observed noisy signal based on generalized
Gaussian distribution prior and additivity of cumulants},
booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012},
pages = {4049--4052},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/ICASSP.2012.6288807},
doi = {10.1109/ICASSP.2012.6288807},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/WakisakaSST12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/YamamotoTDSS12,
author = {Kenzo Yamamoto and
Tomoki Toda and
Hironori Doi and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Statistical approach to voice quality control in esophageal speech
enhancement},
booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012},
pages = {4497--4500},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/ICASSP.2012.6287949},
doi = {10.1109/ICASSP.2012.6287949},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/YamamotoTDSS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MiyazakiSISK12,
author = {Ryoichi Miyazaki and
Hiroshi Saruwatari and
Takayuki Inoue and
Kiyohiro Shikano and
Kazunobu Kondo},
title = {Musical-noise-free speech enhancement: Theory and evaluation},
booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012},
pages = {4565--4568},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/ICASSP.2012.6288934},
doi = {10.1109/ICASSP.2012.6288934},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MiyazakiSISK12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MajimaTFKMSS12,
author = {Haruka Majima and
Rafael Torres and
Yoko Fujita and
Hiromichi Kawanami and
Tomoko Matsui and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Spoken Inquiry Discrimination Using Bag-of-Words for Speech-Oriented
Guidance System},
booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
Communication Association, Portland, Oregon, USA, September 9-13,
2012},
pages = {2097--2100},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-559},
doi = {10.21437/INTERSPEECH.2012-559},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MajimaTFKMSS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KuboKSS12,
author = {Keigo Kubo and
Hiromichi Kawanami and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Evaluation of Many-to-Many Alignment Algorithm by Automatic Pronunciation
Annotation Using Web Text Mining},
booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
Communication Association, Portland, Oregon, USA, September 9-13,
2012},
pages = {2318--2321},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-608},
doi = {10.21437/INTERSPEECH.2012-608},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KuboKSS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isspa/MiyazakiSSK12,
author = {Ryoichi Miyazaki and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Kazunobu Kondo},
title = {Musical-noise-free blind speech extraction using ICA-based noise estimation
and iterative spectral subtraction},
booktitle = {11th International Conference on Information Science, Signal Processing
and their Applications, {ISSPA} 2012, Montreal, QC, Canada, July 2-5,
2012},
pages = {286--291},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/ISSPA.2012.6310561},
doi = {10.1109/ISSPA.2012.6310561},
timestamp = {Wed, 16 Oct 2019 14:14:56 +0200},
biburl = {https://dblp.org/rec/conf/isspa/MiyazakiSSK12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isspit/ItoiMTSS12,
author = {Miyuki Itoi and
Ryoichi Miyazaki and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Blind speech extraction for Non-Audible Murmur speech with speaker's
movement noise},
booktitle = {{IEEE} International Symposium on Signal Processing and Information
Technology, {ISSPIT} 2012, Ho Chi Minh City, Vietnam, December 12-15,
2012},
pages = {320--325},
publisher = {{IEEE} Computer Society},
year = {2012},
url = {https://doi.org/10.1109/ISSPIT.2012.6621308},
doi = {10.1109/ISSPIT.2012.6621308},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/isspit/ItoiMTSS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwaenc/KaneharaSMSK12,
author = {Suzumi Kanehara and
Hiroshi Saruwatari and
Ryoichi Miyazaki and
Kiyohiro Shikano and
Kazunobu Kondo},
title = {Theoretical Analysis of Musical Noise Generation in Noise Reduction
Methods with Decision-Directed a Priori {SNR} Estimator},
booktitle = {{IWAENC} 2012 - International Workshop on Acoustic Signal Enhancement,
Proceedings, {RWTH} Aachen University, Germany, September 4th - 6th,
2012},
publisher = {VDE-Verlag},
year = {2012},
url = {http://www.vde-verlag.de/proceedings-de/453451049.html},
timestamp = {Fri, 17 May 2013 18:34:53 +0200},
biburl = {https://dblp.org/rec/conf/iwaenc/KaneharaSMSK12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwaenc/MiyazakiSSK12,
author = {Ryoichi Miyazaki and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Kazunobu Kondo},
title = {Musical-Noise-Free Blind Speech Extraction Using ICA-Based Noise Estimation
with Channel Selection},
booktitle = {{IWAENC} 2012 - International Workshop on Acoustic Signal Enhancement,
Proceedings, {RWTH} Aachen University, Germany, September 4th - 6th,
2012},
publisher = {VDE-Verlag},
year = {2012},
url = {http://www.vde-verlag.de/proceedings-de/453451056.html},
timestamp = {Fri, 17 May 2013 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iwaenc/MiyazakiSSK12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwsds/HaraKSS12,
author = {Sunao Hara and
Hiromichi Kawanami and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Joseph Mariani and
Sophie Rosset and
Martine Garnier{-}Rizet and
Laurence Devillers},
title = {Development of a Toolkit Handling Multiple Speech-Oriented Guidance
Agents for Mobile Applications},
booktitle = {Natural Interaction with Robots, Knowbots and Smartphones, 4th International
Workshop on Spoken Dialogue Systems, {IWSDS} 2012, Paris, France,
November 28-30, 2012},
pages = {79--85},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-1-4614-8280-2\_8},
doi = {10.1007/978-1-4614-8280-2\_8},
timestamp = {Thu, 29 Apr 2021 13:34:52 +0200},
biburl = {https://dblp.org/rec/conf/iwsds/HaraKSS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwsds/TorresKMSS12,
author = {Rafael Torres and
Hiromichi Kawanami and
Tomoko Matsui and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Joseph Mariani and
Sophie Rosset and
Martine Garnier{-}Rizet and
Laurence Devillers},
title = {Topic Classification of Spoken Inquiries Using Transductive Support
Vector Machine},
booktitle = {Natural Interaction with Robots, Knowbots and Smartphones, 4th International
Workshop on Spoken Dialogue Systems, {IWSDS} 2012, Paris, France,
November 28-30, 2012},
pages = {261--267},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-1-4614-8280-2\_23},
doi = {10.1007/978-1-4614-8280-2\_23},
timestamp = {Thu, 29 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iwsds/TorresKMSS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwsds/MajimaTKHMSS12,
author = {Haruka Majima and
Rafael Torres and
Hiromichi Kawanami and
Sunao Hara and
Tomoko Matsui and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Joseph Mariani and
Sophie Rosset and
Martine Garnier{-}Rizet and
Laurence Devillers},
title = {Evaluation of Invalid Input Discrimination Using Bag-of-Words for
Speech-Oriented Guidance System},
booktitle = {Natural Interaction with Robots, Knowbots and Smartphones, 4th International
Workshop on Spoken Dialogue Systems, {IWSDS} 2012, Paris, France,
November 28-30, 2012},
pages = {389--397},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-1-4614-8280-2\_35},
doi = {10.1007/978-1-4614-8280-2\_35},
timestamp = {Thu, 29 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iwsds/MajimaTKHMSS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/KamadoHSSS11,
author = {Noriyoshi Kamado and
Haruhide Hokari and
Shoji Shimada and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Sound Field Reproduction by Wavefront Synthesis Using Directly Aligned
Multi Point Control},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {94-A},
number = {3},
pages = {907--920},
year = {2011},
url = {https://doi.org/10.1587/transfun.E94.A.907},
doi = {10.1587/TRANSFUN.E94.A.907},
timestamp = {Sat, 11 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/KamadoHSSS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/SaruwatariITISK11,
author = {Hiroshi Saruwatari and
Yohei Ishikawa and
Yu Takahashi and
Takayuki Inoue and
Kiyohiro Shikano and
Kazunobu Kondo},
title = {Musical Noise Controllable Algorithm of Channelwise Spectral Subtraction
and Adaptive Beamforming Based on Higher Order Statistics},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {19},
number = {6},
pages = {1457--1466},
year = {2011},
url = {https://doi.org/10.1109/TASL.2010.2091636},
doi = {10.1109/TASL.2010.2091636},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/SaruwatariITISK11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/InoueSTSK11,
author = {Takayuki Inoue and
Hiroshi Saruwatari and
Yu Takahashi and
Kiyohiro Shikano and
Kazunobu Kondo},
title = {Theoretical Analysis of Musical Noise in Generalized Spectral Subtraction
Based on Higher Order Statistics},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {19},
number = {6},
pages = {1770--1779},
year = {2011},
url = {https://doi.org/10.1109/TASL.2010.2098871},
doi = {10.1109/TASL.2010.2098871},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/InoueSTSK11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/IshiiTSSN11,
author = {Shunta Ishii and
Tomoki Toda and
Hiroshi Saruwatari and
Sakriani Sakti and
Satoshi Nakamura},
editor = {David Nahamoo and
Michael Picheny},
title = {Blind noise suppression for Non-Audible Murmur recognition with stereo
signal processing},
booktitle = {2011 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
{ASRU} 2011, Waikoloa, HI, USA, December 11-15, 2011},
pages = {494--499},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ASRU.2011.6163981},
doi = {10.1109/ASRU.2011.6163981},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/asru/IshiiTSSN11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/KondoTHSNT11,
author = {Kazunobu Kondo and
Yu Takahashi and
Seiichi Hashimoto and
Hiroshi Saruwatari and
Takanori Nishino and
Kazuya Takeda},
title = {Efficient blind speech separation suitable for embedded devices},
booktitle = {Proceedings of the 19th European Signal Processing Conference, {EUSIPCO}
2011, Barcelona, Spain, August 29 - Sept. 2, 2011},
pages = {2319--2323},
publisher = {{IEEE}},
year = {2011},
url = {https://ieeexplore.ieee.org/document/7074189/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/KondoTHSNT11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/NawataKSS11,
author = {Hiroyuki Nawata and
Noriyoshi Kamado and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Automatic musical thumbnailing based on audio object localization
and its evaluation},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2011, May 22-27, 2011, Prague Congress
Center, Prague, Czech Republic},
pages = {41--44},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5946323},
doi = {10.1109/ICASSP.2011.5946323},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/NawataKSS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KamadoSS11,
author = {Noriyoshi Kamado and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Robust sound field reproduction integrating multi-point sound field
control and wave field synthesis},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2011, May 22-27, 2011, Prague Congress
Center, Prague, Czech Republic},
pages = {441--444},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5946435},
doi = {10.1109/ICASSP.2011.5946435},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/KamadoSS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/InoueSSK11,
author = {Takayuki Inoue and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Kazunobu Kondo},
title = {Theoretical analysis of musical noise in Wiener filtering family via
higher-order statistics},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2011, May 22-27, 2011, Prague Congress
Center, Prague, Czech Republic},
pages = {5076--5079},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5947498},
doi = {10.1109/ICASSP.2011.5947498},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/InoueSSK11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/DoiNTSS11,
author = {Hironori Doi and
Keigo Nakamura and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {An evaluation of alaryngeal speech enhancement methods based on voice
conversion techniques},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2011, May 22-27, 2011, Prague Congress
Center, Prague, Czech Republic},
pages = {5136--5139},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5947513},
doi = {10.1109/ICASSP.2011.5947513},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/DoiNTSS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/BabaniTSS11,
author = {Denis Babani and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Acoustic model training for non-audible murmur recognition using transformed
normal speech data},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2011, May 22-27, 2011, Prague Congress
Center, Prague, Czech Republic},
pages = {5224--5227},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5947535},
doi = {10.1109/ICASSP.2011.5947535},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/BabaniTSS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MiyazakiSS11,
author = {Ryoichi Miyazaki and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Theoretical Analysis of Musical Noise and Speech Distortion in Structure-Generalized
Parametric Blind Spatial Subtraction Array},
booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011},
pages = {341--344},
publisher = {{ISCA}},
year = {2011},
url = {https://doi.org/10.21437/Interspeech.2011-125},
doi = {10.21437/INTERSPEECH.2011-125},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MiyazakiSS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WakisakaSST11,
author = {Ryo Wakisaka and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Tomoya Takatani},
title = {Blind Speech Prior Estimation for Generalized Minimum Mean-Square
Error Short-Time Spectral Amplitude Estimator},
booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011},
pages = {361--364},
publisher = {{ISCA}},
year = {2011},
url = {https://doi.org/10.21437/Interspeech.2011-130},
doi = {10.21437/INTERSPEECH.2011-130},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/WakisakaSST11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HattoriTKSS11,
author = {Nobuhiko Hattori and
Tomoki Toda and
Hisashi Kawai and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Speaker-Adaptive Speech Synthesis Based on Eigenvoice Conversion and
Language-Dependent Prosodic Conversion in Speech-to-Speech Translation},
booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011},
pages = {2769--2772},
publisher = {{ISCA}},
year = {2011},
url = {https://doi.org/10.21437/Interspeech.2011-693},
doi = {10.21437/INTERSPEECH.2011-693},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HattoriTKSS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isspit/SaruwatariHHWST11,
author = {Hiroshi Saruwatari and
Nobuhisa Hirata and
Toshiyuki Hatta and
Ryo Wakisaka and
Kiyohiro Shikano and
Tomoya Takatani},
editor = {Adel Elmaghraby and
Dimitrios N. Serpanos},
title = {Semi-blind speech extraction for robot using visual information and
noise statistics},
booktitle = {2011 {IEEE} International Symposium on Signal Processing and Information
Technology, {ISSPIT} 2011, Bilbao, Spain, December 14-17, 2011},
pages = {264--269},
publisher = {{IEEE} Computer Society},
year = {2011},
url = {https://doi.org/10.1109/ISSPIT.2011.6151571},
doi = {10.1109/ISSPIT.2011.6151571},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/isspit/SaruwatariHHWST11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ejasp/TakahashiSSK10,
author = {Yu Takahashi and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Kazunobu Kondo},
title = {Musical-Noise Analysis in Methods of Integrating Microphone Array
and Spectral Subtraction Based on Higher-Order Statistics},
journal = {{EURASIP} J. Adv. Signal Process.},
volume = {2010},
year = {2010},
url = {https://doi.org/10.1155/2010/431347},
doi = {10.1155/2010/431347},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ejasp/TakahashiSSK10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/OhtaniTSS10,
author = {Yamato Ohtani and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Adaptive Training for Voice Conversion Based on Eigenvoices},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {93-D},
number = {6},
pages = {1589--1598},
year = {2010},
url = {https://doi.org/10.1587/transinf.E93.D.1589},
doi = {10.1587/TRANSINF.E93.D.1589},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/OhtaniTSS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/NakamuraTSS10,
author = {Keigo Nakamura and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Evaluation of Extremely Small Sound Source Signals Used in Speaking-Aid
System with Statistical Voice Conversion},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {93-D},
number = {7},
pages = {1909--1917},
year = {2010},
url = {https://doi.org/10.1587/transinf.E93.D.1909},
doi = {10.1587/TRANSINF.E93.D.1909},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/NakamuraTSS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/DoiNTSS10,
author = {Hironori Doi and
Keigo Nakamura and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Esophageal Speech Enhancement Based on Statistical Voice Conversion
with Gaussian Mixture Models},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {93-D},
number = {9},
pages = {2472--2482},
year = {2010},
url = {https://doi.org/10.1587/transinf.E93.D.2472},
doi = {10.1587/TRANSINF.E93.D.2472},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/DoiNTSS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/OhtaniTSS10a,
author = {Yamato Ohtani and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Improvements of the One-to-Many Eigenvoice Conversion System},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {93-D},
number = {9},
pages = {2491--2499},
year = {2010},
url = {https://doi.org/10.1587/transinf.E93.D.2491},
doi = {10.1587/TRANSINF.E93.D.2491},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/OhtaniTSS10a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cogip/IshikawaSTSK10,
author = {Yohei Ishikawa and
Hiroshi Saruwatari and
Yu Takahashi and
Kiyohiro Shikano and
Kazunobu Kondo},
title = {Musical noise controllable algorithm of channelwise spectral subtraction
and beamforming based on higher-order statistics criterion},
booktitle = {2nd International Workshop on Cognitive Information Processing, {CIP}
2010, Elba, Italy, 14-16 June, 2010},
pages = {81--86},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/CIP.2010.5604226},
doi = {10.1109/CIP.2010.5604226},
timestamp = {Wed, 16 Oct 2019 14:14:48 +0200},
biburl = {https://dblp.org/rec/conf/cogip/IshikawaSTSK10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/InoueTSSK10,
author = {Takayuki Inoue and
Yu Takahashi and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Kazunobu Kondo},
title = {Theoretical analysis of musical noise in generalized spectral subtraction:
Why should not use power/amplitude subtraction?},
booktitle = {18th European Signal Processing Conference, {EUSIPCO} 2010, Aalborg,
Denmark, August 23-27, 2010},
pages = {994--998},
publisher = {{IEEE}},
year = {2010},
url = {https://ieeexplore.ieee.org/document/7096577/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/InoueTSSK10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/EvenSST10,
author = {Jani Even and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Tomoya Takatani},
title = {Blind signal extraction based joint suppression of diffuse background
noise and late reverberation},
booktitle = {18th European Signal Processing Conference, {EUSIPCO} 2010, Aalborg,
Denmark, August 23-27, 2010},
pages = {1534--1538},
publisher = {{IEEE}},
year = {2010},
url = {https://ieeexplore.ieee.org/document/7096554/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/EvenSST10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ica/SaruwatariOTS10,
author = {Hiroshi Saruwatari and
Ryoi Okamoto and
Yu Takahashi and
Kiyohiro Shikano},
editor = {Vincent Vigneron and
Vicente Zarzoso and
Eric Moreau and
R{\'{e}}mi Gribonval and
Emmanuel Vincent},
title = {Blind Speech Extraction Combining Generalized {MMSE} {STSA} Estimator
and ICA-Based Noise and Speech Probability Density Function Estimations},
booktitle = {Latent Variable Analysis and Signal Separation - 9th International
Conference, {LVA/ICA} 2010, St. Malo, France, September 27-30, 2010.
Proceedings},
series = {Lecture Notes in Computer Science},
volume = {6365},
pages = {49--56},
publisher = {Springer},
year = {2010},
url = {https://doi.org/10.1007/978-3-642-15995-4\_7},
doi = {10.1007/978-3-642-15995-4\_7},
timestamp = {Mon, 05 Feb 2024 20:32:12 +0100},
biburl = {https://dblp.org/rec/conf/ica/SaruwatariOTS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TakahashiSSK10,
author = {Yu Takahashi and
Hiroshi Saruwatari and
Hiroshi Shikano and
Kazunobu Kondo},
title = {Theoretical musical-noise analysis and its generalization for methods
of integrating beamforming and spectral subtraction based on higher-order
statistics},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {93--96},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5496173},
doi = {10.1109/ICASSP.2010.5496173},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/TakahashiSSK10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/EvenSST10,
author = {Jani Even and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Tomoya Takatani},
title = {Complex Newton algorithm for blind signal extraction of speech in
diffuse noise},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {213--216},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5496023},
doi = {10.1109/ICASSP.2010.5496023},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/EvenSST10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/DoiNTSS10,
author = {Hironori Doi and
Keigo Nakamura and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Statistical approach to enhancing esophageal speech based on Gaussian
mixture models},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {4250--4253},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495676},
doi = {10.1109/ICASSP.2010.5495676},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/DoiNTSS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/EvenSST10a,
author = {Jani Even and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Tomoya Takatani},
title = {Speech enhancement in presence of diffuse background noise: Why using
blind signal extraction?},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {4770--4773},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495160},
doi = {10.1109/ICASSP.2010.5495160},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/EvenSST10a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/OkamotoTSS10,
author = {Ryoi Okamoto and
Yu Takahashi and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {{MMSE} {STSA} estimator with nonstationary noise estimation based
on {ICA} for high-quality speech enhancement},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {4778--4781},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495162},
doi = {10.1109/ICASSP.2010.5495162},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/OkamotoTSS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/OhtaniTSS10,
author = {Yamato Ohtani and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Non-parallel training for many-to-many eigenvoice conversion},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {4822--4825},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5495139},
doi = {10.1109/ICASSP.2010.5495139},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/OhtaniTSS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/EvenISH10,
author = {Jani Even and
Carlos Toshinori Ishi and
Hiroshi Saruwatari and
Norihiro Hagita},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {Close speaker cancellation for suppression of non-stationary background
noise for hands-free speech interface},
booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
Communication Association, Makuhari, Chiba, Japan, September 26-30,
2010},
pages = {977--980},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-326},
doi = {10.21437/INTERSPEECH.2010-326},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/EvenISH10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TorresTKMSS10,
author = {Rafael Torres and
Shota Takeuchi and
Hiromichi Kawanami and
Tomoko Matsui and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {Comparison of methods for topic classification in a speech-oriented
guidance system},
booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
Communication Association, Makuhari, Chiba, Japan, September 26-30,
2010},
pages = {1261--1264},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-397},
doi = {10.21437/INTERSPEECH.2010-397},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/TorresTKMSS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NakamuraTSS10,
author = {Keigo Nakamura and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {The use of air-pressure sensor in electrolaryngeal speech enhancement
based on statistical voice conversion},
booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
Communication Association, Makuhari, Chiba, Japan, September 26-30,
2010},
pages = {1628--1631},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-471},
doi = {10.21437/INTERSPEECH.2010-471},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/NakamuraTSS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/OhtaTOSS10,
author = {Kumi Ohta and
Tomoki Toda and
Yamato Ohtani and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {Adaptive voice-quality control based on one-to-many eigenvoice conversion},
booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
Communication Association, Makuhari, Chiba, Japan, September 26-30,
2010},
pages = {2158--2161},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-595},
doi = {10.21437/INTERSPEECH.2010-595},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/OhtaTOSS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iros/SawadaESST10,
author = {Hiroshi Sawada and
Jani Even and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Tomoya Takatani},
title = {Improvement of speech recognition performance for spoken-oriented
robot dialog system using end-fire array},
booktitle = {2010 {IEEE/RSJ} International Conference on Intelligent Robots and
Systems, October 18-22, 2010, Taipei, Taiwan},
pages = {970--975},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/IROS.2010.5648924},
doi = {10.1109/IROS.2010.5648924},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/iros/SawadaESST10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ssw/HayashidaTOSS10,
author = {Chie Hayashida and
Tomoki Toda and
Yamato Ohtani and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Yoshinori Sagisaka and
Keiichi Tokuda},
title = {Linear transformation approaches to many-to-one voice conversion},
booktitle = {The Seventh {ISCA} Tutorial and Research Workshop on Speech Synthesis,
Kyoto, Japan, September 22-24, 2010},
pages = {74--79},
publisher = {{ISCA}},
year = {2010},
url = {http://www.isca-speech.org/archive/ssw7/ssw7\_074.html},
timestamp = {Tue, 16 Nov 2021 11:36:19 +0100},
biburl = {https://dblp.org/rec/conf/ssw/HayashidaTOSS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/dsp/PrasadSS09,
author = {Rajkishore Prasad and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Enhancement of speech signals separated from their convolutive mixture
by {FDICA} algorithm},
journal = {Digit. Signal Process.},
volume = {19},
number = {1},
pages = {127--133},
year = {2009},
url = {https://doi.org/10.1016/j.dsp.2008.01.007},
doi = {10.1016/J.DSP.2008.01.007},
timestamp = {Thu, 20 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/dsp/PrasadSS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/GomezTSS09,
author = {Randy Gomez and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Techniques in rapid unsupervised speaker adaptation based on HMM-Sufficient
Statistics},
journal = {Speech Commun.},
volume = {51},
number = {1},
pages = {42--57},
year = {2009},
url = {https://doi.org/10.1016/j.specom.2008.05.014},
doi = {10.1016/J.SPECOM.2008.05.014},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/speech/GomezTSS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/TakahashiTOSS09,
author = {Yu Takahashi and
Tomoya Takatani and
Keiichi Osako and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Blind Spatial Subtraction Array for Speech Enhancement in Noisy Environment},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {17},
number = {4},
pages = {650--664},
year = {2009},
url = {https://doi.org/10.1109/TASL.2008.2011517},
doi = {10.1109/TASL.2008.2011517},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/TakahashiTOSS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/EvenSS09,
author = {Jani Even and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Enhanced wiener post-processing based on partial projection back of
the blind signal separation noise estimate},
booktitle = {17th European Signal Processing Conference, {EUSIPCO} 2009, Glasgow,
Scotland, UK, August 24-28, 2009},
pages = {1442--1446},
publisher = {{IEEE}},
year = {2009},
url = {https://ieeexplore.ieee.org/document/7077808/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/EvenSS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HiekataMIHZTSS09,
author = {Takashi Hiekata and
Takashi Morita and
Youhei Ikeda and
Hiroshi Hashimoto and
Ruoyu Zhang and
Yu Takahashi and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Multiple ICA-based real-time blind source extraction applied to handy
size microphone},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {121--124},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4959535},
doi = {10.1109/ICASSP.2009.4959535},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/HiekataMIHZTSS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TakahashiUSSK09,
author = {Yu Takahashi and
Yoshihisa Uemura and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Kazunobu Kondo},
title = {Musical noise analysis based on higher order statistics for microphone
array and nonlinear signal processing},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {229--232},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4959562},
doi = {10.1109/ICASSP.2009.4959562},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/TakahashiUSSK09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MiyabeJSS09,
author = {Shigeki Miyabe and
Biing{-}Hwang Juang and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Kernel-based nonlinear independent component analysis for underdetermined
blind source separation},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {1641--1644},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4959915},
doi = {10.1109/ICASSP.2009.4959915},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/MiyabeJSS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TakahashiSFTMMST09,
author = {Yu Takahashi and
Hiroshi Saruwatari and
Yuki Fujihara and
Kentaro Tachibana and
Yoshimitsu Mori and
Shigeki Miyabe and
Kiyohiro Shikano and
Akira Tanaka},
title = {Source adaptive blind signal extraction using closed-form {ICA} for
hands-free robot spoken dialogue system},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {3681--3684},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4960425},
doi = {10.1109/ICASSP.2009.4960425},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/TakahashiSFTMMST09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaruwatariKTTCS09,
author = {Hiroshi Saruwatari and
Hiromichi Kawanami and
Shota Takeuchi and
Yu Takahashi and
Tobias Cincarek and
Kiyohiro Shikano},
title = {Hands-free speech recognition challenge for real-world speech dialogue
systems},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {3729--3732},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4960437},
doi = {10.1109/ICASSP.2009.4960437},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SaruwatariKTTCS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MiyamotoNTSS09,
author = {Daisuke Miyamoto and
Keigo Nakamura and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Acoustic compensation methods for body transmitted speech conversion},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {3901--3904},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4960480},
doi = {10.1109/ICASSP.2009.4960480},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/MiyamotoNTSS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/UemuraTSSK09,
author = {Yoshihisa Uemura and
Yu Takahashi and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Kazunobu Kondo},
title = {Musical noise generation analysis for noise reduction methods based
on spectral subtraction and {MMSE} {STSA} estimation},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {4433--4436},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4960613},
doi = {10.1109/ICASSP.2009.4960613},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/UemuraTSSK09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ida/EvenSS09,
author = {Jani Even and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {T{\"{u}}lay Adali and
Christian Jutten and
Jo{\~{a}}o Marcos Travassos Romano and
Allan Kardec Barros},
title = {Target Speech Enhancement in Presence of Jammer and Diffuse Background
Noise},
booktitle = {Independent Component Analysis and Signal Separation, 8th International
Conference, {ICA} 2009, Paraty, Brazil, March 15-18, 2009. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5441},
pages = {565--572},
publisher = {Springer},
year = {2009},
url = {https://doi.org/10.1007/978-3-642-00599-2\_71},
doi = {10.1007/978-3-642-00599-2\_71},
timestamp = {Tue, 14 May 2019 10:00:49 +0200},
biburl = {https://dblp.org/rec/conf/ida/EvenSS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NakamuraTSS09,
author = {Keigo Nakamura and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Electrolaryngeal speech enhancement based on statistical voice conversion},
booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech
Communication Association, Brighton, United Kingdom, September 6-10,
2009},
pages = {1431--1434},
publisher = {{ISCA}},
year = {2009},
url = {https://doi.org/10.21437/Interspeech.2009-439},
doi = {10.21437/INTERSPEECH.2009-439},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/NakamuraTSS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/OhtaniTSS09,
author = {Yamato Ohtani and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Many-to-many eigenvoice conversion with reference voice},
booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech
Communication Association, Brighton, United Kingdom, September 6-10,
2009},
pages = {1623--1626},
publisher = {{ISCA}},
year = {2009},
url = {https://doi.org/10.21437/Interspeech.2009-485},
doi = {10.21437/INTERSPEECH.2009-485},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/OhtaniTSS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iros/EvenSSST09,
author = {Jani Even and
Hiroshi Sawada and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Tomoya Takatani},
title = {Semi-blind suppression of internal noise for hands-free robot spoken
dialog system},
booktitle = {2009 {IEEE/RSJ} International Conference on Intelligent Robots and
Systems, October 11-15, 2009, St. Louis, MO, {USA}},
pages = {658--663},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/IROS.2009.5354451},
doi = {10.1109/IROS.2009.5354451},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/iros/EvenSSST09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/waspaa/MiyabeMSSN09,
author = {Shigeki Miyabe and
Keisuke Masatoki and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Toshiyuki Nomura},
title = {Temporal quantization of spatial information using directional clustering
for multichannel audio coding},
booktitle = {{IEEE} Workshop on Applications of Signal Processing to Audio and
Acoustics, {WASPAA} '09, New Paltz, NY, USA, October 18-21, 2009},
pages = {261--264},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ASPAA.2009.5346519},
doi = {10.1109/ASPAA.2009.5346519},
timestamp = {Wed, 16 Oct 2019 14:14:57 +0200},
biburl = {https://dblp.org/rec/conf/waspaa/MiyabeMSSN09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/CincarekTSS08,
author = {Tobias Cincarek and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Cost Reduction of Acoustic Modeling for Real-Environment Applications
Using Unsupervised and Selective Training},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {91-D},
number = {3},
pages = {499--507},
year = {2008},
url = {https://doi.org/10.1093/ietisy/e91-d.3.499},
doi = {10.1093/IETISY/E91-D.3.499},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/CincarekTSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/CincarekKNLSS08,
author = {Tobias Cincarek and
Hiromichi Kawanami and
Ryuichi Nisimura and
Akinobu Lee and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Development, Long-Term Operation and Portability of a Real-Environment
Speech-Oriented Guidance System},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {91-D},
number = {3},
pages = {576--587},
year = {2008},
url = {https://doi.org/10.1093/ietisy/e91-d.3.576},
doi = {10.1093/IETISY/E91-D.3.576},
timestamp = {Sat, 11 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/CincarekKNLSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/NaginoSTSS08,
author = {Goshu Nagino and
Makoto Shozakai and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Building an Effective Speech Corpus by Utilizing Statistical Multidimensional
Scaling Method},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {91-D},
number = {3},
pages = {607--614},
year = {2008},
url = {https://doi.org/10.1093/ietisy/e91-d.3.607},
doi = {10.1093/IETISY/E91-D.3.607},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/NaginoSTSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/YaiMSST08,
author = {Yuki Yai and
Shigeki Miyabe and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Yosuke Tatekura},
title = {Rapid Compensation of Temperature Fluctuation Effect for Multichannel
Sound Field Reproduction System},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {91-A},
number = {6},
pages = {1329--1336},
year = {2008},
url = {https://doi.org/10.1093/ietfec/e91-a.6.1329},
doi = {10.1093/IETFEC/E91-A.6.1329},
timestamp = {Sat, 11 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/YaiMSST08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/OsakoMTSS08,
author = {Keiichi Osako and
Yoshimitsu Mori and
Yu Takahashi and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Fast Convergence Blind Source Separation Using Frequency Subband Interpolation
by Null Beamforming},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {91-A},
number = {6},
pages = {1357--1361},
year = {2008},
url = {https://doi.org/10.1093/ietfec/e91-a.6.1357},
doi = {10.1093/IETFEC/E91-A.6.1357},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ieicet/OsakoMTSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/EvenSS08,
author = {Jani Even and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Extension of score function difference for frequency domain blind
source separation},
booktitle = {2008 16th European Signal Processing Conference, {EUSIPCO} 2008, Lausanne,
Switzerland, August 25-29, 2008},
pages = {1--5},
publisher = {{IEEE}},
year = {2008},
url = {https://ieeexplore.ieee.org/document/7080564/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/EvenSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/EvenSS08,
author = {Jani Even and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Frequency domain semi-blind signal separation: application to the
rejection of internal noises},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2008, March 30 - April 4, 2008, Caesars
Palace, Las Vegas, Nevada, {USA}},
pages = {157--160},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4517570},
doi = {10.1109/ICASSP.2008.4517570},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/EvenSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HaraguchiMSSN08,
author = {Yuuki Haraguchi and
Shigeki Miyabe and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Toshiyuki Nomura},
title = {Source-oriented localization control of stereo audio signals based
on blind source separation},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2008, March 30 - April 4, 2008, Caesars
Palace, Las Vegas, Nevada, {USA}},
pages = {177--180},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4517575},
doi = {10.1109/ICASSP.2008.4517575},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HaraguchiMSSN08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/YuyamaMSS08,
author = {Yuuta Yuyama and
Shigeki Miyabe and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Hybrid structure of inverse filtering and DOA-parameterized wavefront
synthesis},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2008, March 30 - April 4, 2008, Caesars
Palace, Las Vegas, Nevada, {USA}},
pages = {401--404},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4517631},
doi = {10.1109/ICASSP.2008.4517631},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/YuyamaMSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/GomezESS08,
author = {Randy Gomez and
Jani Even and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Distant talking robust speech recognition using late reflection components
of room impulse response},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2008, March 30 - April 4, 2008, Caesars
Palace, Las Vegas, Nevada, {USA}},
pages = {4581--4584},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4518676},
doi = {10.1109/ICASSP.2008.4518676},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/GomezESS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TakeuchiCKSS08,
author = {Shota Takeuchi and
Tobias Cincarek and
Hiromichi Kawanami and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Question and answer database optimization using speech recognition
results},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {451--454},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-73},
doi = {10.21437/INTERSPEECH.2008-73},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/TakeuchiCKSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaruwatariTSTCKS08,
author = {Hiroshi Saruwatari and
Yu Takahashi and
Hiroyuki Sakai and
Shota Takeuchi and
Tobias Cincarek and
Hiromichi Kawanami and
Kiyohiro Shikano},
title = {Development and evaluation of hands-free spoken dialogue system for
railway station guidance},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {455--458},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-74},
doi = {10.21437/INTERSPEECH.2008-74},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaruwatariTSTCKS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MuramatsuOTSS08,
author = {Takashi Muramatsu and
Yamato Ohtani and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Low-delay voice conversion based on maximum likelihood estimation
of spectral parameter trajectory},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {1076--1079},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-332},
doi = {10.21437/INTERSPEECH.2008-332},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MuramatsuOTSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/OhtaniTSS08,
author = {Yamato Ohtani and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {An improved one-to-many eigenvoice conversion system},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {1080--1083},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-333},
doi = {10.21437/INTERSPEECH.2008-333},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/OhtaniTSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/OkamotoMKSS08,
author = {Hideki Okamoto and
Tomoko Matsui and
Hiromichi Kawanami and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Speaker verification with non-audible murmur segments by combining
global alignment kernel and penalized logistic regression machine},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {1369--1372},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-398},
doi = {10.21437/INTERSPEECH.2008-398},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/OkamotoMKSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TaniTOSS08,
author = {Daisuke Tani and
Tomoki Toda and
Yamato Ohtani and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Maximum a posteriori adaptation for many-to-one eigenvoice conversion},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {1461--1463},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-421},
doi = {10.21437/INTERSPEECH.2008-421},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/TaniTOSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NakamuraTNSS08,
author = {Keigo Nakamura and
Tomoki Toda and
Yoshitaka Nakajima and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Evaluation of speaking-aid system with voice conversion for laryngectomees
toward its use in practical environments},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {2209--2212},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-577},
doi = {10.21437/INTERSPEECH.2008-577},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/NakamuraTNSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iros/TakahashiSS08,
author = {Yu Takahashi and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Real-time implementation of blind spatial subtraction array for hands-free
robot spoken dialogue system},
booktitle = {2008 {IEEE/RSJ} International Conference on Intelligent Robots and
Systems, September 22-26, 2008, Acropolis Convention Center, Nice,
France},
pages = {1687--1692},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/IROS.2008.4651006},
doi = {10.1109/IROS.2008.4651006},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/iros/TakahashiSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iros/EvenSS08,
author = {Jani Even and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {An improved permutation solver for blind signal separation based front-ends
in robot audition},
booktitle = {2008 {IEEE/RSJ} International Conference on Intelligent Robots and
Systems, September 22-26, 2008, Acropolis Convention Center, Nice,
France},
pages = {2172--2177},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/IROS.2008.4650602},
doi = {10.1109/IROS.2008.4650602},
timestamp = {Mon, 22 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iros/EvenSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/wocci/MiyakeTKSS08,
author = {Jumpei Miyake and
Shota Takeuchi and
Hiromichi Kawanami and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Kay Berkling and
Diego Giuliani and
Alexandros Potamianos},
title = {Language model for the web search task in a spoken dialogue system
for children},
booktitle = {The 1st Workshop on Child, Computer and Interaction, {WOCCI} 2008,
Chania, Crete, Greece, October 23, 2008},
pages = {10},
publisher = {{ISCA}},
year = {2008},
url = {http://www.isca-speech.org/archive/wocci\_2008/woc8\_10.html},
timestamp = {Tue, 16 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/wocci/MiyakeTKSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ejasp/HeracleousKSS07,
author = {Panikos Heracleous and
Tomomi Kaino and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Unvoiced Speech Recognition Using Tissue-Conductive Acoustic Sensor},
journal = {{EURASIP} J. Adv. Signal Process.},
volume = {2007},
year = {2007},
url = {https://doi.org/10.1155/2007/94068},
doi = {10.1155/2007/94068},
timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ejasp/HeracleousKSS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ejasp/MiyabeHSST07,
author = {Shigeki Miyabe and
Yoichi Hinamoto and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Yosuke Tatekura},
title = {Interface for Barge-in Free Spoken Dialogue System Based on Sound
Field Reproduction and Microphone Array},
journal = {{EURASIP} J. Adv. Signal Process.},
volume = {2007},
year = {2007},
url = {https://doi.org/10.1155/2007/57470},
doi = {10.1155/2007/57470},
timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ejasp/MiyabeHSST07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/GomezTSS07,
author = {Randy Gomez and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Reducing Computation Time of the Rapid Unsupervised Speaker Adaptation
Based on HMM-Sufficient Statistics},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {90-D},
number = {2},
pages = {554--561},
year = {2007},
url = {https://doi.org/10.1093/ietisy/e90-d.2.554},
doi = {10.1093/IETISY/E90-D.2.554},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/GomezTSS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/CincarekKSS07,
author = {Tobias Cincarek and
Hiromichi Kawanami and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Sadaoki Furui and
Tatsuya Kawahara},
title = {Development and portability of {ASR} and Q{\&}A modules for real-environment
speech-oriented guidance systems},
booktitle = {{IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
{ASRU} 2007, Kyoto, Japan, December 9-13, 2007},
pages = {520--525},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ASRU.2007.4430166},
doi = {10.1109/ASRU.2007.4430166},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/asru/CincarekKSS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/MiyabeTSST07,
author = {Shigeki Miyabe and
Tomoya Takatani and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Yosuke Tatekura},
title = {Barge-in- and noise-free spoken dialogue interface based on sound
field control and semi-blind source separation},
booktitle = {15th European Signal Processing Conference, {EUSIPCO} 2007, Poznan,
Poland, September 3-7, 2007},
pages = {232--236},
publisher = {{IEEE}},
year = {2007},
url = {https://ieeexplore.ieee.org/document/7098799/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/MiyabeTSST07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TachibanaSMMST07,
author = {Kentaro Tachibana and
Hiroshi Saruwatari and
Yoshimitsu Mori and
Shigeki Miyabe and
Kiyohiro Shikano and
Akira Tanaka},
title = {Efficient Blind Source Separation Combining Closed-Form Second-Order
{ICA} and Nonclosed-Form Higher-Order {ICA}},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April
15-20, 2007},
pages = {45--48},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ICASSP.2007.366612},
doi = {10.1109/ICASSP.2007.366612},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/TachibanaSMMST07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TakahashiTSS07,
author = {Yu Takahashi and
Tomoya Takatani and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Permutation-Robust Structure for ICA-Based Blind Source Extraction},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April
15-20, 2007},
pages = {149--152},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ICASSP.2007.366638},
doi = {10.1109/ICASSP.2007.366638},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/TakahashiTSS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MoriTSSHM07,
author = {Yoshimitsu Mori and
Tomoya Takatani and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Takashi Hiekata and
Takashi Morita},
title = {High-Presence Hearing-Aid System using DSP-Based Real-Time Blind Source
Separation Module},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April
15-20, 2007},
pages = {609--612},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ICASSP.2007.366986},
doi = {10.1109/ICASSP.2007.366986},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MoriTSSHM07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GomezTSS07,
author = {Randy Gomez and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Rapid unsupervised speaker adaptation using single utterance based
on {MLLR} and speaker selection},
booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech
Communication Association, Antwerp, Belgium, August 27-31, 2007},
pages = {262--265},
publisher = {{ISCA}},
year = {2007},
url = {https://doi.org/10.21437/Interspeech.2007-117},
doi = {10.21437/INTERSPEECH.2007-117},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/GomezTSS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/CincarekSTSS07,
author = {Tobias Cincarek and
Izumi Shindo and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Development of preschool children subsystem for {ASR} and q{\&}a
in a real-environment speech-oriented guidance task},
booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech
Communication Association, Antwerp, Belgium, August 27-31, 2007},
pages = {1469--1472},
publisher = {{ISCA}},
year = {2007},
url = {https://doi.org/10.21437/Interspeech.2007-426},
doi = {10.21437/INTERSPEECH.2007-426},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/CincarekSTSS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/OhtaniTSS07,
author = {Yamato Ohtani and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Speaker adaptive training for one-to-many eigenvoice conversion based
on Gaussian mixture model},
booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech
Communication Association, Antwerp, Belgium, August 27-31, 2007},
pages = {1981--1984},
publisher = {{ISCA}},
year = {2007},
url = {https://doi.org/10.21437/Interspeech.2007-554},
doi = {10.21437/INTERSPEECH.2007-554},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/OhtaniTSS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/OkamotoKMKSS07,
author = {Hideki Okamoto and
Mariko Kojima and
Tomoko Matsui and
Hiromichi Kawanami and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Study on speaker verification with non-audible murmur segments},
booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech
Communication Association, Antwerp, Belgium, August 27-31, 2007},
pages = {2017--2020},
publisher = {{ISCA}},
year = {2007},
url = {https://doi.org/10.21437/Interspeech.2007-164},
doi = {10.21437/INTERSPEECH.2007-164},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/OkamotoKMKSS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NakamuraTSS07,
author = {Keigo Nakamura and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Impact of various small sound source signals on voice conversion accuracy
in speech communication aid for laryngectomees},
booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech
Communication Association, Antwerp, Belgium, August 27-31, 2007},
pages = {2517--2520},
publisher = {{ISCA}},
year = {2007},
url = {https://doi.org/10.21437/Interspeech.2007-669},
doi = {10.21437/INTERSPEECH.2007-669},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/NakamuraTSS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isspa/MoriTSSHM07,
author = {Yoshimitsu Mori and
Tomoya Takatani and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Takashi Hiekata and
Takashi Morita},
title = {Noise-robust hands-free speech recognition using SIMO-model-based
blind source separation},
booktitle = {9th International Symposium on Signal Processing and Its Applications,
{ISSPA} 2007, Sharjah, United Arab Emirates, February 12-15, 2007},
pages = {1--4},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ISSPA.2007.4555597},
doi = {10.1109/ISSPA.2007.4555597},
timestamp = {Wed, 16 Oct 2019 14:14:56 +0200},
biburl = {https://dblp.org/rec/conf/isspa/MoriTSSHM07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isspa/TakahashiTSS07,
author = {Yu Takahashi and
Tomoya Takatani and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Robust spatial subtraction array with independent component analysis
for speech enhancement},
booktitle = {9th International Symposium on Signal Processing and Its Applications,
{ISSPA} 2007, Sharjah, United Arab Emirates, February 12-15, 2007},
pages = {1--4},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ISSPA.2007.4555589},
doi = {10.1109/ISSPA.2007.4555589},
timestamp = {Fri, 26 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/isspa/TakahashiTSS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/robocomm/SakaiCKSSL07,
author = {Hiroyuki Sakai and
Tobias Cincarek and
Hiromichi Kawanami and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Akinobu Lee},
editor = {Alan F. T. Winfield and
Jason Redi},
title = {Voice activity detection applied to hands-free spoken dialogue robot
based on decoding using acoustic and language model},
booktitle = {Proceedings of the 1st International Conference on Robot Communication
and Coordination, {ROBOCOMM} 2007, Athens, Greece, October 15-17,
2007},
series = {{ACM} International Conference Proceeding Series},
volume = {318},
pages = {16},
publisher = {{ICST/ACM}},
year = {2007},
url = {https://doi.org/10.4108/ICST.ROBOCOMM2007.2088},
doi = {10.4108/ICST.ROBOCOMM2007.2088},
timestamp = {Tue, 27 Nov 2018 10:40:37 +0100},
biburl = {https://dblp.org/rec/conf/robocomm/SakaiCKSSL07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ssw/OhtaOTSS07,
author = {Kumi Ohta and
Yamato Ohtani and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Petra Wagner and
Julia Abresch and
Stefan Breuer and
Wolfgang Hess},
title = {Regression approaches to voice quality controll based on one-to-many
eigenvoice conversion},
booktitle = {Sixth {ISCA} Workshop on Speech Synthesis, Bonn, Germany, August 22-24,
2007},
pages = {101--106},
publisher = {{ISCA}},
year = {2007},
url = {http://www.isca-speech.org/archive\_open/ssw6/ssw6\_101.html},
timestamp = {Mon, 04 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ssw/OhtaOTSS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ssw/TaniOTSS07,
author = {Daisuke Tani and
Yamato Ohtani and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Petra Wagner and
Julia Abresch and
Stefan Breuer and
Wolfgang Hess},
title = {An evaluation of many-to-one voice conversion algorithms with pre-stored
speaker data sets},
booktitle = {Sixth {ISCA} Workshop on Speech Synthesis, Bonn, Germany, August 22-24,
2007},
pages = {107--112},
publisher = {{ISCA}},
year = {2007},
url = {http://www.isca-speech.org/archive\_open/ssw6/ssw6\_107.html},
timestamp = {Mon, 04 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ssw/TaniOTSS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:books/sp/07/SaruwatariTS07,
author = {Hiroshi Saruwatari and
Tomoya Takatani and
Kiyohiro Shikano},
editor = {Shoji Makino and
Hiroshi Sawada and
Te{-}Won Lee},
title = {SIMO-Model-Based Blind Source Separation - Principle and its Applications},
booktitle = {Blind Speech Separation},
series = {Signals and Communication Technology},
pages = {149--168},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-1-4020-6479-1\_5},
doi = {10.1007/978-1-4020-6479-1\_5},
timestamp = {Fri, 12 Jul 2019 10:51:30 +0200},
biburl = {https://dblp.org/rec/books/sp/07/SaruwatariTS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ejasp/MoriSTUSHIHM06,
author = {Yoshimitsu Mori and
Hiroshi Saruwatari and
Tomoya Takatani and
Satoshi Ukai and
Kiyohiro Shikano and
Takashi Hiekata and
Youhei Ikeda and
Hiroshi Hashimoto and
Takashi Morita},
title = {Blind Separation of Acoustic Signals Combining SIMO-Model-Based Independent
Component Analysis and Binary Masking},
journal = {{EURASIP} J. Adv. Signal Process.},
volume = {2006},
year = {2006},
url = {https://doi.org/10.1155/ASP/2006/34970},
doi = {10.1155/ASP/2006/34970},
timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ejasp/MoriSTUSHIHM06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/MiyabeSST06,
author = {Shigeki Miyabe and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Yosuke Tatekura},
title = {Interface for Barge-in Free Spoken Dialogue System Using Nullspace
Based Sound Field Control and Beamforming},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {89-A},
number = {3},
pages = {716--726},
year = {2006},
url = {https://doi.org/10.1093/ietfec/e89-a.3.716},
doi = {10.1093/IETFEC/E89-A.3.716},
timestamp = {Sat, 11 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/MiyabeSST06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/CincarekTSS06,
author = {Tobias Cincarek and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Utterance-Based Selective Training for the Automatic Creation of Task-Dependent
Acoustic Models},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {89-D},
number = {3},
pages = {962--969},
year = {2006},
url = {https://doi.org/10.1093/ietisy/e89-d.3.962},
doi = {10.1093/IETISY/E89-D.3.962},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/CincarekTSS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/GomezLTSS06,
author = {Randy Gomez and
Akinobu Lee and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Improving Rapid Unsupervised Speaker Adaptation Based on HMM-Sufficient
Statistics in Noisy Environments Using Multi-Template Models},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {89-D},
number = {3},
pages = {998--1005},
year = {2006},
url = {https://doi.org/10.1093/ietisy/e89-d.3.998},
doi = {10.1093/IETISY/E89-D.3.998},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/GomezLTSS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/SaruwatariKNLS06,
author = {Hiroshi Saruwatari and
Toshiya Kawamura and
Tsuyoki Nishikawa and
Akinobu Lee and
Kiyohiro Shikano},
title = {Blind source separation based on a fast-convergence algorithm combining
{ICA} and beamforming},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {14},
number = {2},
pages = {666--678},
year = {2006},
url = {https://doi.org/10.1109/TSA.2005.855832},
doi = {10.1109/TSA.2005.855832},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/SaruwatariKNLS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/MoriTSSHM06,
author = {Yoshimitsu Mori and
Tomoya Takatani and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Takashi Hiekata and
Takashi Morita},
title = {Two-stage blind separation of moving sound sources with pocket-size
real-time {DSP} module},
booktitle = {14th European Signal Processing Conference, {EUSIPCO} 2006, Florence,
Italy, September 4-8, 2006},
pages = {1--5},
publisher = {{IEEE}},
year = {2006},
url = {https://ieeexplore.ieee.org/document/7071689/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/MoriTSSHM06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ica/MoriSTSHM06,
author = {Yoshimitsu Mori and
Hiroshi Saruwatari and
Tomoya Takatani and
Kiyohiro Shikano and
Takashi Hiekata and
Takashi Morita},
editor = {Justinian P. Rosca and
Deniz Erdogmus and
Jos{\'{e}} Carlos Pr{\'{\i}}ncipe and
Simon Haykin},
title = {{ICA} and Binary-Mask-Based Blind Source Separation with Small Directional
Microphones},
booktitle = {Independent Component Analysis and Blind Signal Separation, 6th International
Conference, {ICA} 2006, Charleston, SC, USA, March 5-8, 2006, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {3889},
pages = {649--657},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11679363\_81},
doi = {10.1007/11679363\_81},
timestamp = {Wed, 03 Mar 2021 09:19:59 +0100},
biburl = {https://dblp.org/rec/conf/ica/MoriSTSHM06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MoriTSHM06,
author = {Yoshimitsu Mori and
Tomoya Takatani and
Hiroshi Saruwatari and
Takashi Hiekata and
Takashi Morita},
title = {Blind Source Separation Combining Simo-Ica and Simo-Model-Based Binary
Masking},
booktitle = {2006 {IEEE} International Conference on Acoustics Speech and Signal
Processing, {ICASSP} 2006, Toulouse, France, May 14-19, 2006},
pages = {81--84},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/ICASSP.2006.1661217},
doi = {10.1109/ICASSP.2006.1661217},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MoriTSHM06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MiyabeTMSST06,
author = {Shigeki Miyabe and
Tomoya Takatani and
Yoshimitsu Mori and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Yosuke Tatekura},
title = {Double-Talk Free Spoken Dialogue Interface Combining Sound Field Control
With Semi-Blind Source Separation},
booktitle = {2006 {IEEE} International Conference on Acoustics Speech and Signal
Processing, {ICASSP} 2006, Toulouse, France, May 14-19, 2006},
pages = {809--812},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/ICASSP.2006.1660144},
doi = {10.1109/ICASSP.2006.1660144},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/MiyabeTMSST06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/GomezTSS06,
author = {Randy Gomez and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Improving Rapid Unsupervised Speaker Adaptation Based On Hmm Sufficient
Statistics},
booktitle = {2006 {IEEE} International Conference on Acoustics Speech and Signal
Processing, {ICASSP} 2006, Toulouse, France, May 14-19, 2006},
pages = {1001--1004},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/ICASSP.2006.1660192},
doi = {10.1109/ICASSP.2006.1660192},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/GomezTSS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/CincarekTSS06,
author = {Tobias Cincarek and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Acoustic modeling for spoken dialogue systems based on unsupervised
utterance-based selective training},
booktitle = {{INTERSPEECH} 2006 - ICSLP, Ninth International Conference on Spoken
Language Processing, Pittsburgh, PA, USA, September 17-21, 2006},
publisher = {{ISCA}},
year = {2006},
url = {https://doi.org/10.21437/Interspeech.2006-478},
doi = {10.21437/INTERSPEECH.2006-478},
timestamp = {Thu, 22 Jun 2023 16:42:16 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/CincarekTSS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KojimaMKSS06,
author = {Mariko Kojima and
Tomoko Matsui and
Hiromichi Kawanami and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Speaker verification with non-audible murmur segments},
booktitle = {{INTERSPEECH} 2006 - ICSLP, Ninth International Conference on Spoken
Language Processing, Pittsburgh, PA, USA, September 17-21, 2006},
publisher = {{ISCA}},
year = {2006},
url = {https://doi.org/10.21437/Interspeech.2006-194},
doi = {10.21437/INTERSPEECH.2006-194},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KojimaMKSS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NakamuraTSS06,
author = {Keigo Nakamura and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Speaking aid system for total laryngectomees using voice conversion
of body transmitted artificial speech},
booktitle = {{INTERSPEECH} 2006 - ICSLP, Ninth International Conference on Spoken
Language Processing, Pittsburgh, PA, USA, September 17-21, 2006},
publisher = {{ISCA}},
year = {2006},
url = {https://doi.org/10.21437/Interspeech.2006-419},
doi = {10.21437/INTERSPEECH.2006-419},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/NakamuraTSS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/OhtaniTSS06,
author = {Yamato Ohtani and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Maximum likelihood voice conversion based on {GMM} with {STRAIGHT}
mixed excitation},
booktitle = {{INTERSPEECH} 2006 - ICSLP, Ninth International Conference on Spoken
Language Processing, Pittsburgh, PA, USA, September 17-21, 2006},
publisher = {{ISCA}},
year = {2006},
url = {https://doi.org/10.21437/Interspeech.2006-582},
doi = {10.21437/INTERSPEECH.2006-582},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/OhtaniTSS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/lrec/KatoTSS06,
author = {Tomoyuki Kato and
Tomiki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Nicoletta Calzolari and
Khalid Choukri and
Aldo Gangemi and
Bente Maegaard and
Joseph Mariani and
Jan Odijk and
Daniel Tapias},
title = {Transcription Cost Reduction for Constructing Acoustic Models Using
Acoustic Likelihood Selection Criteria},
booktitle = {Proceedings of the Fifth International Conference on Language Resources
and Evaluation, {LREC} 2006, Genoa, Italy, May 22-28, 2006},
pages = {789--792},
publisher = {European Language Resources Association {(ELRA)}},
year = {2006},
url = {http://www.lrec-conf.org/proceedings/lrec2006/summaries/344.html},
timestamp = {Mon, 19 Aug 2019 15:23:22 +0200},
biburl = {https://dblp.org/rec/conf/lrec/KatoTSS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/AdachiTKSS05,
author = {Kazuki Adachi and
Tomoki Toda and
Hiromichi Kawanami and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Designing Target Cost Function Based on Prosody of Speech Database},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {88-D},
number = {3},
pages = {519--524},
year = {2005},
url = {http://search.ieice.org/bin/summary.php?id=e88-d\_3\_519\&\#38;category=D\&\#38;year=2005\&\#38;lang=E\&\#38;abst=},
timestamp = {Sat, 11 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/AdachiTKSS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/UkaiTSSMS05,
author = {Satoshi Ukai and
Tomoya Takatani and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Ryo Mukai and
Hiroshi Sawada},
title = {Multistage SIMO-Model-Based Blind Source Separation Combining Frequency-Domain
{ICA} and Time-Domain {ICA}},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {88-A},
number = {3},
pages = {642--650},
year = {2005},
url = {https://doi.org/10.1093/ietfec/e88-a.3.642},
doi = {10.1093/IETFEC/E88-A.3.642},
timestamp = {Sat, 11 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/UkaiTSSMS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/AsaiSS05,
author = {Tatsunori Asai and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Interface for Barge-in Free Spoken Dialogue System Combining Adaptive
Sound Field Control and Microphone Array},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {88-A},
number = {6},
pages = {1613--1618},
year = {2005},
url = {https://doi.org/10.1093/ietfec/e88-a.6.1613},
doi = {10.1093/IETFEC/E88-A.6.1613},
timestamp = {Sat, 11 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/AsaiSS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/TakataniUNSS05,
author = {Tomoya Takatani and
Satoshi Ukai and
Tsuyoki Nishikawa and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {A Self-Generator Method for Initial Filters of {SIMO-ICA} Applied
to Blind Separation of Binaural Sound Mixtures},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {88-A},
number = {7},
pages = {1673--1682},
year = {2005},
url = {https://doi.org/10.1093/ietfec/e88-a.7.1673},
doi = {10.1093/IETFEC/E88-A.7.1673},
timestamp = {Sat, 11 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/TakataniUNSS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/PrasadSS05,
author = {Rajkishore Prasad and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Blind Separation of Speech by Fixed-Point {ICA} with Source Adaptive
Negentropy Approximation},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {88-A},
number = {7},
pages = {1683--1692},
year = {2005},
url = {https://doi.org/10.1093/ietfec/e88-a.7.1683},
doi = {10.1093/IETFEC/E88-A.7.1683},
timestamp = {Sat, 11 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/PrasadSS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/TatekuraUSS05,
author = {Yosuke Tatekura and
Shigefumi Urata and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {On-Line Relaxation Algorithm Applicable to Acoustic Fluctuation for
Inverse Filter in Multichannel Sound Reproduction System},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {88-A},
number = {7},
pages = {1747--1756},
year = {2005},
url = {https://doi.org/10.1093/ietfec/e88-a.7.1747},
doi = {10.1093/IETFEC/E88-A.7.1747},
timestamp = {Sat, 11 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/TatekuraUSS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/SaruwatariYTNS05,
author = {Hiroshi Saruwatari and
Hiroaki Yamajo and
Tomoya Takatani and
Tsuyoki Nishikawa and
Kiyohiro Shikano},
title = {Blind Separation and Deconvolution for Convolutive Mixture of Speech
Combining SIMO-Model-Based {ICA} and Multichannel Inverse Filtering},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {88-A},
number = {9},
pages = {2387--2400},
year = {2005},
url = {https://doi.org/10.1093/ietfec/e88-a.9.2387},
doi = {10.1093/IETFEC/E88-A.9.2387},
timestamp = {Sat, 11 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/SaruwatariYTNS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/ArakiMANS05,
author = {Shoko Araki and
Shoji Makino and
Robert Aichner and
Tsuyoki Nishikawa and
Hiroshi Saruwatari},
title = {Subband-Based Blind Separation for Convolutive Mixtures of Speech},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {88-A},
number = {12},
pages = {3593--3603},
year = {2005},
url = {https://doi.org/10.1093/ietfec/e88-a.12.3593},
doi = {10.1093/IETFEC/E88-A.12.3593},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ieicet/ArakiMANS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/npl/PrasadSS05,
author = {Rajkishore Prasad and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Estimation of Shape Parameter of {GGD} Function by Negentropy Matching},
journal = {Neural Process. Lett.},
volume = {22},
number = {3},
pages = {377--389},
year = {2005},
url = {https://doi.org/10.1007/s11063-005-1385-9},
doi = {10.1007/S11063-005-1385-9},
timestamp = {Thu, 09 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/npl/PrasadSS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusai/HeracleousNSS05,
author = {Panikos Heracleous and
Yoshitaka Nakajima and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {G{\'{e}}rard Bailly and
James L. Crowley},
title = {A tissue-conductive acoustic sensor applied in speech recognition
for privacy},
booktitle = {Proceedings of the 2005 joint conference on Smart objects and ambient
intelligence - innovative context-aware services: usages and technologies,
sOc-EUSAI '05, Grenoble, France, October 12-14, 2005},
pages = {93--97},
publisher = {{ACM}},
year = {2005},
url = {https://doi.org/10.1145/1107548.1107577},
doi = {10.1145/1107548.1107577},
timestamp = {Fri, 28 Jan 2022 11:34:47 +0100},
biburl = {https://dblp.org/rec/conf/eusai/HeracleousNSS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/MiyabeSST05,
author = {Shigeki Miyabe and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Yosuke Tatekura},
title = {Barge-in free spoken dialogue interface using nullspace-based sound
field control and beamforming},
booktitle = {13th European Signal Processing Conference, {EUSIPCO} 2005, Antalya,
Turkey, September 4-8, 2005},
pages = {1--4},
publisher = {{IEEE}},
year = {2005},
url = {https://ieeexplore.ieee.org/document/7078179/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/MiyabeSST05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/NishikawaSS05,
author = {Tsuyoki Nishikawa and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Blind separation of more than two sources based on high-convergence
algorithm combining {ICA} and beamforming},
booktitle = {13th European Signal Processing Conference, {EUSIPCO} 2005, Antalya,
Turkey, September 4-8, 2005},
pages = {1--4},
publisher = {{IEEE}},
year = {2005},
url = {https://ieeexplore.ieee.org/document/7078209/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/NishikawaSS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/SaruwatariUTNS05,
author = {Hiroshi Saruwatari and
Satoshi Ukai and
Tomoya Takatani and
Tsuyoki Nishikawa and
Kiyohiro Shikano},
title = {Two-stage blind source separation combining SIMO-model-based {ICA}
and adaptive beamforming},
booktitle = {13th European Signal Processing Conference, {EUSIPCO} 2005, Antalya,
Turkey, September 4-8, 2005},
pages = {1--4},
publisher = {{IEEE}},
year = {2005},
url = {https://ieeexplore.ieee.org/document/7078226/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/SaruwatariUTNS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/TakataniUNSS05,
author = {Tomoya Takatani and
Satoshi Ukai and
Tsuyoki Nishikawa and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Blind separation of binaural sound mixtures using {SIMO-ICA} with
self-generator for initial filter},
booktitle = {13th European Signal Processing Conference, {EUSIPCO} 2005, Antalya,
Turkey, September 4-8, 2005},
pages = {1--4},
publisher = {{IEEE}},
year = {2005},
url = {https://ieeexplore.ieee.org/document/7078282/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/TakataniUNSS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/UkaiTNS05,
author = {Satoshi Ukai and
Tomoya Takatani and
Tsuyoki Nishikawa and
Hiroshi Saruwatari},
title = {Blind source separation combining SIMO-model-based {ICA} and adaptive
beamforming},
booktitle = {2005 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '05, Philadelphia, Pennsylvania, USA, March 18-23,
2005},
pages = {85--88},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/ICASSP.2005.1415652},
doi = {10.1109/ICASSP.2005.1415652},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/UkaiTNS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icde/SaruwatariSNLSKSS05,
author = {Hiroshi Saruwatari and
Katsuyuki Sawai and
Tsuyoki Nishikawa and
Akinobu Lee and
Kiyohiro Shikano and
Atsunobu Kaminuma and
Masao Sakata and
Daisuke Saitoh},
title = {Speech Enhancement Based on Blind Source Separation in Car Environments},
booktitle = {Proceedings of the 21st International Conference on Data Engineering
Workshops, {ICDE} 2005, 5-8 April 2005, Tokyo, Japan},
pages = {1205},
publisher = {{IEEE} Computer Society},
year = {2005},
url = {https://doi.org/10.1109/ICDE.2005.289},
doi = {10.1109/ICDE.2005.289},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icde/SaruwatariSNLSKSS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GomezLSS05,
author = {Randy Gomez and
Akinobu Lee and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Rapid unsupervised speaker adaptation based on multi-template {HMM}
sufficient statistics in noisy environments},
booktitle = {{INTERSPEECH} 2005 - Eurospeech, 9th European Conference on Speech
Communication and Technology, Lisbon, Portugal, September 4-8, 2005},
pages = {293--296},
publisher = {{ISCA}},
year = {2005},
url = {https://doi.org/10.21437/Interspeech.2005-161},
doi = {10.21437/INTERSPEECH.2005-161},
timestamp = {Thu, 22 Jun 2023 16:42:16 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/GomezLSS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaitohKSNL05,
author = {Daisuke Saitoh and
Atsunobu Kaminuma and
Hiroshi Saruwatari and
Tsuyoki Nishikawa and
Akinobu Lee},
title = {Speech extraction in a car interior using frequency-domain {ICA} with
rapid filter adaptations},
booktitle = {{INTERSPEECH} 2005 - Eurospeech, 9th European Conference on Speech
Communication and Technology, Lisbon, Portugal, September 4-8, 2005},
pages = {2301--2304},
publisher = {{ISCA}},
year = {2005},
url = {https://doi.org/10.21437/Interspeech.2005-736},
doi = {10.21437/INTERSPEECH.2005-736},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaitohKSNL05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HeracleousKSS05,
author = {Panikos Heracleous and
Tomomi Kaino and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Investigating the role of the Lombard reflex in non-audible murmur
{(NAM)} recognition},
booktitle = {{INTERSPEECH} 2005 - Eurospeech, 9th European Conference on Speech
Communication and Technology, Lisbon, Portugal, September 4-8, 2005},
pages = {2649--2652},
publisher = {{ISCA}},
year = {2005},
url = {https://doi.org/10.21437/Interspeech.2005-251},
doi = {10.21437/INTERSPEECH.2005-251},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HeracleousKSS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HeracleousKSS05a,
author = {Panikos Heracleous and
Tomomi Kaino and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Applications of {NAM} microphones in speech recognition for privacy
in human-machine communication},
booktitle = {{INTERSPEECH} 2005 - Eurospeech, 9th European Conference on Speech
Communication and Technology, Lisbon, Portugal, September 4-8, 2005},
pages = {3041--3044},
publisher = {{ISCA}},
year = {2005},
url = {https://doi.org/10.21437/Interspeech.2005-149},
doi = {10.21437/INTERSPEECH.2005-149},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HeracleousKSS05a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iros/TakataniUNSS05,
author = {Tomoya Takatani and
Satoshi Ukai and
Tsuyoki Nishikawa and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Blind sound scene decomposition for robot audition using SIMO-model-based
{ICA}},
booktitle = {2005 {IEEE/RSJ} International Conference on Intelligent Robots and
Systems, Edmonton, Alberta, Canada, August 2-6, 2005},
pages = {2247--2252},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/IROS.2005.1544984},
doi = {10.1109/IROS.2005.1544984},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/iros/TakataniUNSS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iros/SaruwatariMTUSHM05,
author = {Hiroshi Saruwatari and
Yoshimitsu Mori and
Tomoya Takatani and
Satoshi Ukai and
Kiyohiro Shikano and
Takashi Hiekata and
Takashi Morita},
title = {Two-stage blind source separation based on {ICA} and binary masking
for real-time robot audition system},
booktitle = {2005 {IEEE/RSJ} International Conference on Intelligent Robots and
Systems, Edmonton, Alberta, Canada, August 2-6, 2005},
pages = {2303--2308},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/IROS.2005.1544983},
doi = {10.1109/IROS.2005.1544983},
timestamp = {Mon, 22 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iros/SaruwatariMTUSHM05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iros/OhashiNSLS05,
author = {Yasuaki Ohashi and
Tsuyoki Nishikawa and
Hiroshi Saruwatari and
Akinobu Lee and
Kiyohiro Shikano},
title = {Noise-robust hands-free speech recognition based on spatial subtraction
array and known noise superimposition},
booktitle = {2005 {IEEE/RSJ} International Conference on Intelligent Robots and
Systems, Edmonton, Alberta, Canada, August 2-6, 2005},
pages = {2328--2332},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/IROS.2005.1545036},
doi = {10.1109/IROS.2005.1545036},
timestamp = {Mon, 22 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iros/OhashiNSLS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ar/PrasadSS04,
author = {Rajkishore Prasad and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Robots that can hear, understand and talk},
journal = {Adv. Robotics},
volume = {18},
number = {5},
pages = {533--564},
year = {2004},
url = {https://doi.org/10.1163/156855304774195064},
doi = {10.1163/156855304774195064},
timestamp = {Sat, 30 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ar/PrasadSS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieiceee/PrasadSS04,
author = {Rajkishore Prasad and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Negentropy based voice-activity detection for noise estimation in
very low {SNR} condition},
journal = {{IEICE} Electron. Express},
volume = {1},
number = {16},
pages = {495--500},
year = {2004},
url = {https://doi.org/10.1587/elex.1.495},
doi = {10.1587/ELEX.1.495},
timestamp = {Fri, 10 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieiceee/PrasadSS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/HeracleousNLSS04,
author = {Panikos Heracleous and
Yoshitaka Nakajima and
Akinobu Lee and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Audible (normal) speech and inaudible murmur recognition using {NAM}
microphone},
booktitle = {2004 12th European Signal Processing Conference, Vienna, Austria,
September 6-10, 2004},
pages = {329--332},
publisher = {{IEEE}},
year = {2004},
url = {https://ieeexplore.ieee.org/document/7079711/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/HeracleousNLSS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/YamajoSTNS04,
author = {Hiroaki Yamajo and
Hiroshi Saruwatari and
Tomoya Takatani and
Tsuyoki Nishikawa and
Kiyohiro Shikano},
title = {Evaluation of blind separation and deconvolution for binaural-sound
mixtures using SIMO-model-based {ICA}},
booktitle = {2004 12th European Signal Processing Conference, Vienna, Austria,
September 6-10, 2004},
pages = {1709--1712},
publisher = {{IEEE}},
year = {2004},
url = {https://ieeexplore.ieee.org/document/7080136/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/YamajoSTNS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/TatekuraUSS04,
author = {Yosuke Tatekura and
Shigefumi Urata and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {On-line adaptive algorithm to acoustic fluctuation for inverse filter
relaxation in sound reproduction system},
booktitle = {2004 12th European Signal Processing Conference, Vienna, Austria,
September 6-10, 2004},
pages = {1765--1768},
publisher = {{IEEE}},
year = {2004},
url = {https://ieeexplore.ieee.org/document/7079842/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/TatekuraUSS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ica/UkaiSTSMS04,
author = {Satoshi Ukai and
Hiroshi Saruwatari and
Tomoya Takatani and
Kiyohiro Shikano and
Ryo Mukai and
Hiroshi Sawada},
editor = {Carlos Garc{\'{\i}}a Puntonet and
Alberto Prieto},
title = {Evaluation of Multistage SIMO-Model-Based Blind Source Separation
Combining Frequency-Domain {ICA} and Time-Domain {ICA}},
booktitle = {Independent Component Analysis and Blind Signal Separation, Fifth
International Conference, {ICA} 2004, Granada, Spain, September 22-24,
2004, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {3195},
pages = {626--633},
publisher = {Springer},
year = {2004},
url = {https://doi.org/10.1007/978-3-540-30110-3\_80},
doi = {10.1007/978-3-540-30110-3\_80},
timestamp = {Tue, 14 May 2019 10:00:52 +0200},
biburl = {https://dblp.org/rec/conf/ica/UkaiSTSMS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ica/PrasadSS04,
author = {Rajkishore Prasad and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Carlos Garc{\'{\i}}a Puntonet and
Alberto Prieto},
title = {Single Channel Speech Enhancement: {MAP} Estimation Using {GGD} Prior
Under Blind Setup},
booktitle = {Independent Component Analysis and Blind Signal Separation, Fifth
International Conference, {ICA} 2004, Granada, Spain, September 22-24,
2004, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {3195},
pages = {873--880},
publisher = {Springer},
year = {2004},
url = {https://doi.org/10.1007/978-3-540-30110-3\_110},
doi = {10.1007/978-3-540-30110-3\_110},
timestamp = {Wed, 24 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ica/PrasadSS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ica/NishikawaSSK04,
author = {Tsuyoki Nishikawa and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Atsunobu Kaminuma},
editor = {Carlos Garc{\'{\i}}a Puntonet and
Alberto Prieto},
title = {Stable and Low-Distortion Algorithm Based on Overdetermined Blind
Separation for Convolutive Mixtures of Speech},
booktitle = {Independent Component Analysis and Blind Signal Separation, Fifth
International Conference, {ICA} 2004, Granada, Spain, September 22-24,
2004, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {3195},
pages = {881--888},
publisher = {Springer},
year = {2004},
url = {https://doi.org/10.1007/978-3-540-30110-3\_111},
doi = {10.1007/978-3-540-30110-3\_111},
timestamp = {Wed, 24 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ica/NishikawaSSK04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/UkaiSTMS04,
author = {Satoshi Ukai and
Hiroshi Saruwatari and
Tomoya Takatani and
Ryo Mukai and
Hiroshi Sawada},
title = {Multistage SIMO-model-based blind source separation combining frequency-domain
{ICA} and time-domain {ICA}},
booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004},
pages = {109--112},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/ICASSP.2004.1326775},
doi = {10.1109/ICASSP.2004.1326775},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/UkaiSTMS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TakataniNSS04,
author = {Tomoya Takatani and
Tsuyoki Nishikawa and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Blind separation of binaural sound mixtures using SIMO-model-based
independent component analysis},
booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004},
pages = {113--116},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/ICASSP.2004.1326776},
doi = {10.1109/ICASSP.2004.1326776},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/TakataniNSS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/NishikawaASS04,
author = {Tsuyoki Nishikawa and
Hiroshi Abe and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Overdetermined blind separation for convolutive mixtures of speech
based on multistage {ICA} using subarray processing},
booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004},
pages = {225--228},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/ICASSP.2004.1325963},
doi = {10.1109/ICASSP.2004.1325963},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/NishikawaASS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/NisimuraLSS04,
author = {Ryuichi Nisimura and
Akinobu Lee and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Public speech-oriented guidance system with adult and child discrimination
capability},
booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004},
pages = {433--436},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/ICASSP.2004.1326015},
doi = {10.1109/ICASSP.2004.1326015},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/NisimuraLSS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PrasadSS04,
author = {Rajkishore Prasad and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {{MAP} estimation of speech spectral component under {GGD} a priori},
booktitle = {{ISCA} Tutorial and Research Workshop on Statistical and Perceptual
Audio Processing, ICC, Jeju, Korea, October 3, 2004},
pages = {115},
publisher = {{ISCA}},
year = {2004},
url = {https://www.isca-speech.org/archive\_open/sapa\_04/sap4\_115.html},
timestamp = {Tue, 11 Jul 2023 11:45:03 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PrasadSS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LeeNNSS04,
author = {Akinobu Lee and
Keisuke Nakamura and
Ryuichi Nisimura and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Noise robust real world spoken dialogue system using {GMM} based rejection
of unintended inputs},
booktitle = {{INTERSPEECH} 2004 - ICSLP, 8th International Conference on Spoken
Language Processing, Jeju Island, Korea, October 4-8, 2004},
pages = {173--176},
publisher = {{ISCA}},
year = {2004},
url = {https://doi.org/10.21437/Interspeech.2004-111},
doi = {10.21437/INTERSPEECH.2004-111},
timestamp = {Thu, 22 Jun 2023 16:42:17 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LeeNNSS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HeracleousNLSS04,
author = {Panikos Heracleous and
Yoshitaka Nakajima and
Akinobu Lee and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Non-audible murmur {(NAM)} speech recognition using a stethoscopic
{NAM} microphone},
booktitle = {{INTERSPEECH} 2004 - ICSLP, 8th International Conference on Spoken
Language Processing, Jeju Island, Korea, October 4-8, 2004},
pages = {1469--1472},
publisher = {{ISCA}},
year = {2004},
url = {https://doi.org/10.21437/Interspeech.2004-559},
doi = {10.21437/INTERSPEECH.2004-559},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HeracleousNLSS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GomezLSS04,
author = {Randy Gomez and
Akinobu Lee and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Robust speech recognition with spectral subtraction in low {SNR}},
booktitle = {{INTERSPEECH} 2004 - ICSLP, 8th International Conference on Spoken
Language Processing, Jeju Island, Korea, October 4-8, 2004},
pages = {2077--2080},
publisher = {{ISCA}},
year = {2004},
url = {https://doi.org/10.21437/Interspeech.2004-633},
doi = {10.21437/INTERSPEECH.2004-633},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/GomezLSS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AsaiMSS04,
author = {Tatsunori Asai and
Shigeki Miyabe and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Interface for barge-in free spoken dialogue system using adaptive
sound field control},
booktitle = {{INTERSPEECH} 2004 - ICSLP, 8th International Conference on Spoken
Language Processing, Jeju Island, Korea, October 4-8, 2004},
pages = {2665--2668},
publisher = {{ISCA}},
year = {2004},
url = {https://doi.org/10.21437/Interspeech.2004-708},
doi = {10.21437/INTERSPEECH.2004-708},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/AsaiMSS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/lrec/AdachiTKSS04,
author = {Kazuki Adachi and
Tomoki Toda and
Hiromichi Kawanami and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Perceptual Evaluation of Quality Deterioration Owing to Prosody Modification},
booktitle = {Proceedings of the Fourth International Conference on Language Resources
and Evaluation, {LREC} 2004, May 26-28, 2004, Lisbon, Portugal},
publisher = {European Language Resources Association},
year = {2004},
url = {http://www.lrec-conf.org/proceedings/lrec2004/summaries/681.htm},
timestamp = {Mon, 19 Aug 2019 15:22:43 +0200},
biburl = {https://dblp.org/rec/conf/lrec/AdachiTKSS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ejasp/SaruwatariKTINS03,
author = {Hiroshi Saruwatari and
Satoshi Kurita and
Kazuya Takeda and
Fumitada Itakura and
Tsuyoki Nishikawa and
Kiyohiro Shikano},
title = {Blind Source Separation Combining Independent Component Analysis and
Beamforming},
journal = {{EURASIP} J. Adv. Signal Process.},
volume = {2003},
number = {11},
pages = {1135--1146},
year = {2003},
url = {https://doi.org/10.1155/S1110865703305104},
doi = {10.1155/S1110865703305104},
timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ejasp/SaruwatariKTINS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ejasp/ArakiMHMNS03,
author = {Shoko Araki and
Shoji Makino and
Yoichi Hinamoto and
Ryo Mukai and
Tsuyoki Nishikawa and
Hiroshi Saruwatari},
title = {Equivalence between Frequency-Domain Blind Source Separation and Frequency-Domain
Adaptive Beamforming for Convolutive Mixtures},
journal = {{EURASIP} J. Adv. Signal Process.},
volume = {2003},
number = {11},
pages = {1157--1166},
year = {2003},
url = {https://doi.org/10.1155/S1110865703305074},
doi = {10.1155/S1110865703305074},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ejasp/ArakiMHMNS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieiceta/SaruwatariKNS03,
author = {Hiroshi Saruwatari and
Toshiya Kawamura and
Tsuyoki Nishikawa and
Kiyohiro Shikano},
title = {Fast-Convergence Algorithm for Blind Source Separation Based on Array
Signal Processing},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {86-A},
number = {3},
pages = {634--639},
year = {2003},
url = {http://search.ieice.org/bin/summary.php?id=e86-a\_3\_634},
timestamp = {Tue, 08 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieiceta/SaruwatariKNS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieiceta/NishikawaSS03,
author = {Tsuyoki Nishikawa and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Blind Source Separation of Acoustic Signals Based on Multistage {ICA}
Combining Frequency-Domain {ICA} and Time-Domain {ICA}},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {86-A},
number = {4},
pages = {846--858},
year = {2003},
url = {http://search.ieice.org/bin/summary.php?id=e86-a\_4\_846},
timestamp = {Tue, 08 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieiceta/NishikawaSS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieiceta/NishikawaSS03a,
author = {Tsuyoki Nishikawa and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Stable Learning Algorithm for Blind Separation of Temporally Correlated
Acoustic Signals Combining Multistage {ICA} and Linear Prediction},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {86-A},
number = {8},
pages = {2028--2036},
year = {2003},
url = {http://search.ieice.org/bin/summary.php?id=e86-a\_8\_2028},
timestamp = {Tue, 08 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieiceta/NishikawaSS03a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/ArakiMMNS03,
author = {Shoko Araki and
Ryo Mukai and
Shoji Makino and
Tsuyoki Nishikawa and
Hiroshi Saruwatari},
title = {The fundamental limitation of frequency domain blind source separation
for convolutive mixtures of speech},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {11},
number = {2},
pages = {109--116},
year = {2003},
url = {https://doi.org/10.1109/TSA.2003.809193},
doi = {10.1109/TSA.2003.809193},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/ArakiMMNS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TakataniNS03,
author = {Tomoya Takatani and
Tsuyoki Nishikawa and
Hiroshi Saruwatari},
title = {Blind source separation based on binaural {ICA}},
booktitle = {2003 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '03, Hong Kong, April 6-10, 2003},
pages = {321--324},
publisher = {{IEEE}},
year = {2003},
url = {https://doi.org/10.1109/ICASSP.2003.1199940},
doi = {10.1109/ICASSP.2003.1199940},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/TakataniNS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HinamotoMSS03,
author = {Yoichi Hinamoto and
Kouichi Mino and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Interface for barge-in free spoken dialogue system based on sound
field control and microphone array},
booktitle = {2003 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '03, Hong Kong, April 6-10, 2003},
pages = {505--508},
publisher = {{IEEE}},
year = {2003},
url = {https://doi.org/10.1109/ICASSP.2003.1200017},
doi = {10.1109/ICASSP.2003.1200017},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HinamotoMSS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ArakiMANS03,
author = {Shoko Araki and
Shoji Makino and
Robert Aichner and
Tsuyoki Nishikawa and
Hiroshi Saruwatari},
title = {Subband based blind source separation for convolutive mixtures of
speech},
booktitle = {2003 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '03, Hong Kong, April 6-10, 2003},
pages = {509--512},
publisher = {{IEEE}},
year = {2003},
url = {https://doi.org/10.1109/ICASSP.2003.1200018},
doi = {10.1109/ICASSP.2003.1200018},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ArakiMANS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/YamajoSTNS03,
author = {Hiroaki Yamajo and
Hiroshi Saruwatari and
Tomoya Takatani and
Tsuyoki Nishikawa and
Kiyohiro Shikano},
title = {Blind separation and deconvolution for convolutive mixture of speech
using SIMO-model-based {ICA} and multichannel inverse filtering},
booktitle = {8th European Conference on Speech Communication and Technology, {EUROSPEECH}
2003 - {INTERSPEECH} 2003, Geneva, Switzerland, September 1-4, 2003},
pages = {537--540},
publisher = {{ISCA}},
year = {2003},
url = {https://doi.org/10.21437/Eurospeech.2003-220},
doi = {10.21437/EUROSPEECH.2003-220},
timestamp = {Thu, 22 Jun 2023 16:42:17 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/YamajoSTNS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/YamadeLSS03,
author = {Shingo Yamade and
Akinobu Lee and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Unsupervised speaker adaptation based on {HMM} sufficient statistics
in various noisy environments},
booktitle = {8th European Conference on Speech Communication and Technology, {EUROSPEECH}
2003 - {INTERSPEECH} 2003, Geneva, Switzerland, September 1-4, 2003},
pages = {1493--1496},
publisher = {{ISCA}},
year = {2003},
url = {https://doi.org/10.21437/Eurospeech.2003-434},
doi = {10.21437/EUROSPEECH.2003-434},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/YamadeLSS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ShiraishiTKSS03,
author = {Tatsuya Shiraishi and
Tomoki Toda and
Hiromichi Kawanami and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Simple designing methods of corpus-based visual speech synthesis},
booktitle = {8th European Conference on Speech Communication and Technology, {EUROSPEECH}
2003 - {INTERSPEECH} 2003, Geneva, Switzerland, September 1-4, 2003},
pages = {2241--2244},
publisher = {{ISCA}},
year = {2003},
url = {https://doi.org/10.21437/Eurospeech.2003-627},
doi = {10.21437/EUROSPEECH.2003-627},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ShiraishiTKSS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KawanamiITSS03,
author = {Hiromichi Kawanami and
Yohei Iwami and
Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {GMM-based voice conversion applied to emotional speech synthesis},
booktitle = {8th European Conference on Speech Communication and Technology, {EUROSPEECH}
2003 - {INTERSPEECH} 2003, Geneva, Switzerland, September 1-4, 2003},
pages = {2401--2404},
publisher = {{ISCA}},
year = {2003},
url = {https://doi.org/10.21437/Eurospeech.2003-661},
doi = {10.21437/EUROSPEECH.2003-661},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KawanamiITSS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isspa/TakataniNSS03,
author = {Tomoya Takatani and
Tsuyoki Nishikawa and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {High-fidelity blind separation for convolutive mixture of acoustic
signals using SIMO-model-based independent component analysis},
booktitle = {Seventh International Symposium on Signal Processing and Its Applications,
{ISSPA} 2003, July 1-4, 2003, Paris, France, Proceedings, Volume 2},
pages = {77--80},
publisher = {{IEEE}},
year = {2003},
url = {https://doi.org/10.1109/ISSPA.2003.1224819},
doi = {10.1109/ISSPA.2003.1224819},
timestamp = {Wed, 16 Oct 2019 14:14:56 +0200},
biburl = {https://dblp.org/rec/conf/isspa/TakataniNSS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nnsp/SaruwatariYTNS03,
author = {Hiroshi Saruwatari and
Hiroaki Yamajo and
Tomoya Takatani and
Tsuyoki Nishikawa and
Kiyohiro Shikano},
title = {Blind separation and deconvolution of {MIMO} system driven by colored
inputs using SIMO-model-based {ICA} with information-geometric learning},
booktitle = {{NNSP} 2003, {IEEE} {XIII} Workshop on Neural Networks for Signal
Processing, Toulouse, France, September 17-19, 2003},
pages = {379--388},
publisher = {{IEEE}},
year = {2003},
url = {https://doi.org/10.1109/NNSP.2003.1318037},
doi = {10.1109/NNSP.2003.1318037},
timestamp = {Wed, 16 Oct 2019 14:14:54 +0200},
biburl = {https://dblp.org/rec/conf/nnsp/SaruwatariYTNS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nolisp/NishikawaSS03,
author = {Tsuyoki Nishikawa and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Stable learning algorithm for low-distortion blind separation of real
speech mixture combining multistage {ICA} and linear prediction},
booktitle = {{ITRW} on Non-Linear Speech Processing, {NOLISP} 03, Le Croisic, France,
May 20-23, 2003},
pages = {8},
publisher = {{ISCA}},
year = {2003},
url = {http://www.isca-speech.org/archive\_open/nolisp03/nl03\_008.html},
timestamp = {Tue, 08 Apr 2014 18:09:26 +0200},
biburl = {https://dblp.org/rec/conf/nolisp/NishikawaSS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieiceta/TatekuraSS02,
author = {Yosuke Tatekura and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Sound Reproduction System Including Adaptive Compensation of Temperature
Fluctuation Effect for Broad-Band Sound Control},
journal = {{IEICE} Trans. Fundam. Electron. Commun. Comput. Sci.},
volume = {85-A},
number = {8},
pages = {1851--1860},
year = {2002},
url = {http://search.ieice.org/bin/summary.php?id=e85-a\_8\_1851},
timestamp = {Wed, 09 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieiceta/TatekuraSS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/NishikawaSS02,
author = {Tsuyoki Nishikawa and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Comparison of time-domain ICA, frequency-domain {ICA} and multistage
{ICA} for blind source separation},
booktitle = {11th European Signal Processing Conference, {EUSIPCO} 2002, Toulouse,
France, September 3-6, 2002},
pages = {1--4},
publisher = {{IEEE}},
year = {2002},
url = {https://ieeexplore.ieee.org/document/7071932/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/NishikawaSS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/SaruwatariKSSKS02,
author = {Hiroshi Saruwatari and
Toshiya Kawamura and
Katsuyuki Sawai and
Kiyohiro Shikano and
Atsunobu Kaminuma and
Masao Sakata},
title = {Evaluation of fast-convergence algorithm for ICA-based blind source
separation of real convolutive mixture},
booktitle = {11th European Signal Processing Conference, {EUSIPCO} 2002, Toulouse,
France, September 3-6, 2002},
pages = {1--4},
publisher = {{IEEE}},
year = {2002},
url = {https://ieeexplore.ieee.org/document/7072211/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/SaruwatariKSSKS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/TatekuraSS02,
author = {Yosuke Tatekura and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Adaptive compensation of temperature fluctuation effect in sound reproduction
system},
booktitle = {11th European Signal Processing Conference, {EUSIPCO} 2002, Toulouse,
France, September 3-6, 2002},
pages = {1--4},
publisher = {{IEEE}},
year = {2002},
url = {https://ieeexplore.ieee.org/document/7071928/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/TatekuraSS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/NishikawaSS02,
author = {Tsuyoki Nishikawa and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Bund source separation based on Multi-Stage {ICA} combining frequency-domain
{ICA} and time-domain {ICA}},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2002, May 13-17 2002, Orlando, Florida,
{USA}},
pages = {917--920},
publisher = {{IEEE}},
year = {2002},
url = {https://doi.org/10.1109/ICASSP.2002.5743889},
doi = {10.1109/ICASSP.2002.5743889},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/NishikawaSS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaruwatariKSKS02,
author = {Hiroshi Saruwatari and
Toshiya Kawamura and
Katsuyuki Sawai and
Atsunobu Kaminuma and
Masao Sakata},
title = {Blind source separation based on fast-convergence algorithm using
{ICA} and beamforming for real convolutive mixture},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2002, May 13-17 2002, Orlando, Florida,
{USA}},
pages = {921--924},
publisher = {{IEEE}},
year = {2002},
url = {https://doi.org/10.1109/ICASSP.2002.5743890},
doi = {10.1109/ICASSP.2002.5743890},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SaruwatariKSKS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ArakiHMNMS02,
author = {Shoko Araki and
Yoichi Hinamoto and
Shoji Makino and
Tsuyoki Nishikawa and
Ryo Mukai and
Hiroshi Saruwatari},
title = {Equivalence between frequency domain blind source separation and frequency
domain adaptive beamforming},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2002, May 13-17 2002, Orlando, Florida,
{USA}},
pages = {1785--1788},
publisher = {{IEEE}},
year = {2002},
url = {https://doi.org/10.1109/ICASSP.2002.5744969},
doi = {10.1109/ICASSP.2002.5744969},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ArakiHMNMS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdsp/TatekuraSS02,
author = {Yosuke Tatekura and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Sound reproduction system with adaptive compensation of temperature
fluctuation effect},
booktitle = {14th International Conference on Digital Signal Processing, {DSP}
2002, Santorini, Greece, July 1-3, 2002},
pages = {989--992},
publisher = {{IEEE}},
year = {2002},
url = {https://doi.org/10.1109/ICDSP.2002.1028256},
doi = {10.1109/ICDSP.2002.1028256},
timestamp = {Tue, 02 Feb 2021 15:02:09 +0100},
biburl = {https://dblp.org/rec/conf/icdsp/TatekuraSS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmcs/NakamuraHAKYNKIS02,
author = {Satoshi Nakamura and
Kazuo Hiyane and
Futoshi Asano and
Yutaka Kaneda and
Takeshi Yamada and
Takanobu Nishiura and
Tetsunori Kobayashi and
Shiro Ise and
Hiroshi Saruwatari},
title = {Design and collection of acoustic sound data for hands-free speech
recognition and sound scene understanding},
booktitle = {Proceedings of the 2002 {IEEE} International Conference on Multimedia
and Expo, {ICME} 2002, Lausanne, Switzerland. August 26-29, 2002.
Volume {II}},
pages = {161--164},
publisher = {{IEEE} Computer Society},
year = {2002},
url = {https://doi.org/10.1109/ICME.2002.1035537},
doi = {10.1109/ICME.2002.1035537},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icmcs/NakamuraHAKYNKIS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/YamadeMBLSS02,
author = {Shingo Yamade and
Kanako Matsunami and
Akira Baba and
Akinobu Lee and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {John H. L. Hansen and
Bryan L. Pellom},
title = {Spectral subtraction in noisy environments applied to speaker adaptation
based on {HMM} sufficient statistics},
booktitle = {7th International Conference on Spoken Language Processing, {ICSLP2002}
- {INTERSPEECH} 2002, Denver, Colorado, USA, September 16-20, 2002},
pages = {1045--1048},
publisher = {{ISCA}},
year = {2002},
url = {https://doi.org/10.21437/ICSLP.2002-33},
doi = {10.21437/ICSLP.2002-33},
timestamp = {Thu, 22 Jun 2023 16:42:18 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/YamadeMBLSS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaruwatariSLSKS02,
author = {Hiroshi Saruwatari and
Katsuyuki Sawai and
Akinobu Lee and
Kiyohiro Shikano and
Atsunobu Kaminuma and
Masao Sakata},
editor = {John H. L. Hansen and
Bryan L. Pellom},
title = {Speech enhancement in car environment using blind source separation},
booktitle = {7th International Conference on Spoken Language Processing, {ICSLP2002}
- {INTERSPEECH} 2002, Denver, Colorado, USA, September 16-20, 2002},
pages = {1781--1784},
publisher = {{ISCA}},
year = {2002},
url = {https://doi.org/10.21437/ICSLP.2002-262},
doi = {10.21437/ICSLP.2002-262},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaruwatariSLSKS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LeeMSS02,
author = {Akinobu Lee and
Yuichiro Mera and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {John H. L. Hansen and
Bryan L. Pellom},
title = {Selective multi-path acoustic model based on database likelihoods},
booktitle = {7th International Conference on Spoken Language Processing, {ICSLP2002}
- {INTERSPEECH} 2002, Denver, Colorado, USA, September 16-20, 2002},
pages = {2661--2664},
publisher = {{ISCA}},
year = {2002},
url = {https://doi.org/10.21437/ICSLP.2002-356},
doi = {10.21437/ICSLP.2002-356},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LeeMSS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iros/NisimuraULSSM02,
author = {Ryuichi Nisimura and
Takashi Uchida and
Akinobu Lee and
Hiroshi Saruwatari and
Kiyohiro Shikano and
Yoshio Matsumoto},
title = {{ASKA:} receptionist robot with speech dialogue system},
booktitle = {{IEEE/RSJ} International Conference on Intelligent Robots and Systems,
Lausanne, Switzerland, September 30 - October 4, 2002},
pages = {1314--1319},
publisher = {{IEEE}},
year = {2002},
url = {https://doi.org/10.1109/IRDS.2002.1043936},
doi = {10.1109/IRDS.2002.1043936},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/iros/NisimuraULSSM02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nnsp/AichnerAMNS02,
author = {Robert Aichner and
Shoko Araki and
Shoji Makino and
Tsuyoki Nishikawa and
Hiroshi Saruwatari},
title = {Time domain blind source separation of non-stationary convolved signals
by utilizing geometric beamforming},
booktitle = {Proceedings of the 12th {IEEE} Workshop on Neural Networks for Signal
Processing, {NNSP} 2002, Martigny, Valais, Switzerland, September
4-6, 2002},
pages = {445--454},
publisher = {{IEEE}},
year = {2002},
url = {https://doi.org/10.1109/NNSP.2002.1030056},
doi = {10.1109/NNSP.2002.1030056},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nnsp/AichnerAMNS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TodaSS01,
author = {Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Voice conversion algorithm based on Gaussian mixture model with dynamic
frequency warping of {STRAIGHT} spectrum},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} 2001, 7-11 May, 2001, Salt Palace Convention Center, Salt
Lake City, Utah, USA, Proceedings},
pages = {841--844},
publisher = {{IEEE}},
year = {2001},
url = {https://doi.org/10.1109/ICASSP.2001.941046},
doi = {10.1109/ICASSP.2001.941046},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/TodaSS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaruwatariKT01,
author = {Hiroshi Saruwatari and
Satoshi Kurita and
Kazuya Takeda},
title = {Blind source separation combining frequency-domain {ICA} and beamforming},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} 2001, 7-11 May, 2001, Salt Palace Convention Center, Salt
Lake City, Utah, USA, Proceedings},
pages = {2733--2736},
publisher = {{IEEE}},
year = {2001},
url = {https://doi.org/10.1109/ICASSP.2001.940211},
doi = {10.1109/ICASSP.2001.940211},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SaruwatariKT01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ArakiMNS01,
author = {Shoko Araki and
Shoji Makino and
Tsuyoki Nishikawa and
Hiroshi Saruwatari},
title = {Fundamental limitation of frequency domain blind source separation
for convolutive mixture of speech},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} 2001, 7-11 May, 2001, Salt Palace Convention Center, Salt
Lake City, Utah, USA, Proceedings},
pages = {2737--2740},
publisher = {{IEEE}},
year = {2001},
url = {https://doi.org/10.1109/ICASSP.2001.940212},
doi = {10.1109/ICASSP.2001.940212},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/ArakiMNS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KamiyanagidaSTI01,
author = {Hidekazu Kamiyanagida and
Hiroshi Saruwatari and
Kazuya Takeda and
Fumitada Itakura},
title = {Direction of arrival estimation based on nonlinear microphone array},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} 2001, 7-11 May, 2001, Salt Palace Convention Center, Salt
Lake City, Utah, USA, Proceedings},
pages = {3033--3036},
publisher = {{IEEE}},
year = {2001},
url = {https://doi.org/10.1109/ICASSP.2001.940297},
doi = {10.1109/ICASSP.2001.940297},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/KamiyanagidaSTI01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TodaSS01,
author = {Tomoki Toda and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Paul Dalsgaard and
B{\o}rge Lindberg and
Henrik Benner and
Zheng{-}Hua Tan},
title = {High quality voice conversion based on Gaussian mixture model with
dynamic frequency warping},
booktitle = {{EUROSPEECH} 2001 Scandinavia, 7th European Conference on Speech Communication
and Technology, 2nd {INTERSPEECH} Event, Aalborg, Denmark, September
3-7, 2001},
pages = {349--352},
publisher = {{ISCA}},
year = {2001},
url = {https://doi.org/10.21437/Eurospeech.2001-108},
doi = {10.21437/EUROSPEECH.2001-108},
timestamp = {Thu, 22 Jun 2023 16:42:18 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/TodaSS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/YamadaBYMLSS01,
author = {Miichi Yamada and
Akira Baba and
Shinichi Yoshizawa and
Yuichiro Mera and
Akinobu Lee and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Paul Dalsgaard and
B{\o}rge Lindberg and
Henrik Benner and
Zheng{-}Hua Tan},
title = {Unsupervised noisy environment adaptation algorithm using {MLLR} and
speaker selection},
booktitle = {{EUROSPEECH} 2001 Scandinavia, 7th European Conference on Speech Communication
and Technology, 2nd {INTERSPEECH} Event, Aalborg, Denmark, September
3-7, 2001},
pages = {869--872},
publisher = {{ISCA}},
year = {2001},
url = {https://doi.org/10.21437/Eurospeech.2001-265},
doi = {10.21437/EUROSPEECH.2001-265},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/YamadaBYMLSS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NisimuraKKNLSS01,
author = {Ryuichi Nisimura and
Kumiko Komatsu and
Yuka Kuroda and
Kentaro Nagatomo and
Akinobu Lee and
Hiroshi Saruwatari and
Kiyohiro Shikano},
editor = {Paul Dalsgaard and
B{\o}rge Lindberg and
Henrik Benner and
Zheng{-}Hua Tan},
title = {Automatic n-gram language model creation from web resources},
booktitle = {{EUROSPEECH} 2001 Scandinavia, 7th European Conference on Speech Communication
and Technology, 2nd {INTERSPEECH} Event, Aalborg, Denmark, September
3-7, 2001},
pages = {2127--2130},
publisher = {{ISCA}},
year = {2001},
url = {https://doi.org/10.21437/Eurospeech.2001-501},
doi = {10.21437/EUROSPEECH.2001-501},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/NisimuraKKNLSS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ArakiMMS01,
author = {Shoko Araki and
Shoji Makino and
Ryo Mukai and
Hiroshi Saruwatari},
editor = {Paul Dalsgaard and
B{\o}rge Lindberg and
Henrik Benner and
Zheng{-}Hua Tan},
title = {Equivalence between frequency domain blind source separation and frequency
domain adaptive null beamformers},
booktitle = {{EUROSPEECH} 2001 Scandinavia, 7th European Conference on Speech Communication
and Technology, 2nd {INTERSPEECH} Event, Aalborg, Denmark, September
3-7, 2001},
pages = {2595--2598},
publisher = {{ISCA}},
year = {2001},
url = {https://doi.org/10.21437/Eurospeech.2001-607},
doi = {10.21437/EUROSPEECH.2001-607},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ArakiMMS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaruwatariKS01,
author = {Hiroshi Saruwatari and
Toshiya Kawamura and
Kiyohiro Shikano},
editor = {Paul Dalsgaard and
B{\o}rge Lindberg and
Henrik Benner and
Zheng{-}Hua Tan},
title = {Blind source separation for speech based on fast-convergence algorithm
with {ICA} and beamforming},
booktitle = {{EUROSPEECH} 2001 Scandinavia, 7th European Conference on Speech Communication
and Technology, 2nd {INTERSPEECH} Event, Aalborg, Denmark, September
3-7, 2001},
pages = {2603--2606},
publisher = {{ISCA}},
year = {2001},
url = {https://doi.org/10.21437/Eurospeech.2001-609},
doi = {10.21437/EUROSPEECH.2001-609},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaruwatariKS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/SaruwatariKTI00,
author = {Hiroshi Saruwatari and
Shoji Kajita and
Kazuya Takeda and
Fumitada Itakura},
title = {Speech enhancement based on noise adaptive nonlinear microphone array},
booktitle = {10th European Signal Processing Conference, {EUSIPCO} 2000, Tampere,
Finland, September 4-8, 2000},
pages = {1--4},
publisher = {{IEEE}},
year = {2000},
url = {https://ieeexplore.ieee.org/document/7075316/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/SaruwatariKTI00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaruwatariKTI00,
author = {Hiroshi Saruwatari and
Shoji Kajita and
Kazuya Takeda and
Fumitada Itakura},
title = {Speech enhancement using nonlinear microphone array with noise adaptive
complementary beamforming},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing.
{ICASSP} 2000, 5-9 June, 2000, Hilton Hotel and Convention Center,
Istanbul, Turkey},
pages = {1049--1052},
publisher = {{IEEE}},
year = {2000},
url = {https://doi.org/10.1109/ICASSP.2000.859143},
doi = {10.1109/ICASSP.2000.859143},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SaruwatariKTI00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KuritaSKTI00,
author = {Satoshi Kurita and
Hiroshi Saruwatari and
Shoji Kajita and
Kazuya Takeda and
Fumitada Itakura},
title = {Evaluation of blind signal separation method using directivity pattern
under reverberant conditions},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing.
{ICASSP} 2000, 5-9 June, 2000, Hilton Hotel and Convention Center,
Istanbul, Turkey},
pages = {3140--3143},
publisher = {{IEEE}},
year = {2000},
url = {https://doi.org/10.1109/ICASSP.2000.861203},
doi = {10.1109/ICASSP.2000.861203},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/KuritaSKTI00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaruwatariKTIS00,
author = {Hiroshi Saruwatari and
Satoshi Kurita and
Kazuya Takeda and
Fumitada Itakura and
Kiyohiro Shikano},
title = {Blind source separation based on subband {ICA} and beamforming},
booktitle = {Sixth International Conference on Spoken Language Processing, {ICSLP}
2000 / {INTERSPEECH} 2000, Beijing, China, October 16-20, 2000},
pages = {94--97},
publisher = {{ISCA}},
year = {2000},
url = {https://doi.org/10.21437/ICSLP.2000-486},
doi = {10.21437/ICSLP.2000-486},
timestamp = {Thu, 22 Jun 2023 16:42:19 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaruwatariKTIS00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TodaLSS00,
author = {Tomoki Toda and
Jinlin Lu and
Hiroshi Saruwatari and
Kiyohiro Shikano},
title = {Straight-based voice conversion algorithm based on Gaussian mixture
model},
booktitle = {Sixth International Conference on Spoken Language Processing, {ICSLP}
2000 / {INTERSPEECH} 2000, Beijing, China, October 16-20, 2000},
pages = {279--282},
publisher = {{ISCA}},
year = {2000},
url = {https://doi.org/10.21437/ICSLP.2000-532},
doi = {10.21437/ICSLP.2000-532},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/TodaLSS00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SaruwatariKTI99,
author = {Hiroshi Saruwatari and
Shoji Kajita and
Kazuya Takeda and
Fumitada Itakura},
title = {Speech enhancement using nonlinear microphone array with complementary
beamforming},
booktitle = {Proceedings of the 1999 {IEEE} International Conference on Acoustics,
Speech, and Signal Processing, {ICASSP} '99, Phoenix, Arizona, USA,
March 15-19, 1999},
pages = {69--72},
publisher = {{IEEE} Computer Society},
year = {1999},
url = {https://doi.org/10.1109/ICASSP.1999.758064},
doi = {10.1109/ICASSP.1999.758064},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/SaruwatariKTI99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/OmuraYSKTI99,
author = {Michiaki Omura and
Motohiko Yada and
Hiroshi Saruwatari and
Shoji Kajita and
Kazuya Takeda and
Fumitada Itakura},
title = {Compensating of room acoustic transfer functions affected by change
of room temperature},
booktitle = {Proceedings of the 1999 {IEEE} International Conference on Acoustics,
Speech, and Signal Processing, {ICASSP} '99, Phoenix, Arizona, USA,
March 15-19, 1999},
pages = {941--944},
publisher = {{IEEE} Computer Society},
year = {1999},
url = {https://doi.org/10.1109/ICASSP.1999.759827},
doi = {10.1109/ICASSP.1999.759827},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/OmuraYSKTI99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SaruwatariKTI99,
author = {Hiroshi Saruwatari and
Shoji Kajita and
Kazuya Takeda and
Fumitada Itakura},
title = {Speech enhancement using nonlinear microphone array under nonstationary
noise conditions},
booktitle = {Sixth European Conference on Speech Communication and Technology,
{EUROSPEECH} 1999, Budapest, Hungary, September 5-9, 1999},
pages = {2567--2570},
publisher = {{ISCA}},
year = {1999},
url = {https://doi.org/10.21437/Eurospeech.1999-564},
doi = {10.21437/EUROSPEECH.1999-564},
timestamp = {Sat, 01 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SaruwatariKTI99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2024-04-25 05:58 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
