BibTeX records: Aren Jansen

download as .bib file

@inproceedings{DBLP:conf/aaai/SuLHKLDSJWVD24,
  author       = {Kun Su and
                  Judith Yue Li and
                  Qingqing Huang and
                  Dima Kuzmin and
                  Joonseok Lee and
                  Chris Donahue and
                  Fei Sha and
                  Aren Jansen and
                  Yu Wang and
                  Mauro Verzetti and
                  Timo I. Denk},
  editor       = {Michael J. Wooldridge and
                  Jennifer G. Dy and
                  Sriraam Natarajan},
  title        = {V2Meow: Meowing to the Visual Beat via Video-to-Music Generation},
  booktitle    = {Thirty-Eighth {AAAI} Conference on Artificial Intelligence, {AAAI}
                  2024, Thirty-Sixth Conference on Innovative Applications of Artificial
                  Intelligence, {IAAI} 2024, Fourteenth Symposium on Educational Advances
                  in Artificial Intelligence, {EAAI} 2014, February 20-27, 2024, Vancouver,
                  Canada},
  pages        = {4952--4960},
  publisher    = {{AAAI} Press},
  year         = {2024},
  url          = {https://doi.org/10.1609/aaai.v38i5.28299},
  doi          = {10.1609/AAAI.V38I5.28299},
  timestamp    = {Tue, 26 Mar 2024 17:04:05 +0100},
  biburl       = {https://dblp.org/rec/conf/aaai/SuLHKLDSJWVD24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/MooreEFHJP23,
  author       = {R. Channing Moore and
                  Daniel P. W. Ellis and
                  Eduardo Fonseca and
                  Shawn Hershey and
                  Aren Jansen and
                  Manoj Plakal},
  title        = {Dataset Balancing Can Hurt Model Performance},
  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/ICASSP49357.2023.10095255},
  doi          = {10.1109/ICASSP49357.2023.10095255},
  timestamp    = {Sun, 05 Nov 2023 16:51:21 +0100},
  biburl       = {https://dblp.org/rec/conf/icassp/MooreEFHJP23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-03238,
  author       = {Judith Yue Li and
                  Aren Jansen and
                  Qingqing Huang and
                  Joonseok Lee and
                  Ravi Ganti and
                  Dima Kuzmin},
  title        = {{MAQA:} {A} Multimodal {QA} Benchmark for Negation},
  journal      = {CoRR},
  volume       = {abs/2301.03238},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2301.03238},
  doi          = {10.48550/ARXIV.2301.03238},
  eprinttype    = {arXiv},
  eprint       = {2301.03238},
  timestamp    = {Tue, 10 Jan 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2301-03238.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-11325,
  author       = {Andrea Agostinelli and
                  Timo I. Denk and
                  Zal{\'{a}}n Borsos and
                  Jesse H. Engel and
                  Mauro Verzetti and
                  Antoine Caillon and
                  Qingqing Huang and
                  Aren Jansen and
                  Adam Roberts and
                  Marco Tagliasacchi and
                  Matthew Sharifi and
                  Neil Zeghidour and
                  Christian Havn{\o} Frank},
  title        = {MusicLM: Generating Music From Text},
  journal      = {CoRR},
  volume       = {abs/2301.11325},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2301.11325},
  doi          = {10.48550/ARXIV.2301.11325},
  eprinttype    = {arXiv},
  eprint       = {2301.11325},
  timestamp    = {Mon, 28 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2301-11325.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-06594,
  author       = {Kun Su and
                  Judith Yue Li and
                  Qingqing Huang and
                  Dima Kuzmin and
                  Joonseok Lee and
                  Chris Donahue and
                  Fei Sha and
                  Aren Jansen and
                  Yu Wang and
                  Mauro Verzetti and
                  Timo I. Denk},
  title        = {V2Meow: Meowing to the Visual Beat via Music Generation},
  journal      = {CoRR},
  volume       = {abs/2305.06594},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2305.06594},
  doi          = {10.48550/ARXIV.2305.06594},
  eprinttype    = {arXiv},
  eprint       = {2305.06594},
  timestamp    = {Wed, 17 May 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2305-06594.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-00079,
  author       = {R. Channing Moore and
                  Daniel P. W. Ellis and
                  Eduardo Fonseca and
                  Shawn Hershey and
                  Aren Jansen and
                  Manoj Plakal},
  title        = {Dataset balancing can hurt model performance},
  journal      = {CoRR},
  volume       = {abs/2307.00079},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2307.00079},
  doi          = {10.48550/ARXIV.2307.00079},
  eprinttype    = {arXiv},
  eprint       = {2307.00079},
  timestamp    = {Mon, 10 Jul 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2307-00079.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jstsp/ZhangPHQGSJXHWZ22,
  author       = {Yu Zhang and
                  Daniel S. Park and
                  Wei Han and
                  James Qin and
                  Anmol Gulati and
                  Joel Shor and
                  Aren Jansen and
                  Yuanzhong Xu and
                  Yanping Huang and
                  Shibo Wang and
                  Zongwei Zhou and
                  Bo Li and
                  Min Ma and
                  William Chan and
                  Jiahui Yu and
                  Yongqiang Wang and
                  Liangliang Cao and
                  Khe Chai Sim and
                  Bhuvana Ramabhadran and
                  Tara N. Sainath and
                  Fran{\c{c}}oise Beaufays and
                  Zhifeng Chen and
                  Quoc V. Le and
                  Chung{-}Cheng Chiu and
                  Ruoming Pang and
                  Yonghui Wu},
  title        = {BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning
                  for Automatic Speech Recognition},
  journal      = {{IEEE} J. Sel. Top. Signal Process.},
  volume       = {16},
  number       = {6},
  pages        = {1519--1532},
  year         = {2022},
  url          = {https://doi.org/10.1109/JSTSP.2022.3182537},
  doi          = {10.1109/JSTSP.2022.3182537},
  timestamp    = {Sun, 13 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/jstsp/ZhangPHQGSJXHWZ22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/npjdm/VieiraVPMJMBP22,
  author       = {Fernando Vieira and
                  Subhashini Venugopalan and
                  Alan S. Premasiri and
                  Maeve McNally and
                  Aren Jansen and
                  Kevin McCloskey and
                  Michael P. Brenner and
                  Steven Perrin},
  title        = {A machine-learning based objective measure for {ALS} disease severity},
  journal      = {npj Digit. Medicine},
  volume       = {5},
  year         = {2022},
  url          = {https://doi.org/10.1038/s41746-022-00588-8},
  doi          = {10.1038/S41746-022-00588-8},
  timestamp    = {Sun, 16 Apr 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/npjdm/VieiraVPMJMBP22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ShorJHPZ22,
  author       = {Joel Shor and
                  Aren Jansen and
                  Wei Han and
                  Daniel S. Park and
                  Yu Zhang},
  title        = {Universal Paralinguistic Speech Representations Using self-Supervised
                  Conformers},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  pages        = {3169--3173},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/ICASSP43922.2022.9747197},
  doi          = {10.1109/ICASSP43922.2022.9747197},
  timestamp    = {Tue, 07 Jun 2022 17:34:47 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/ShorJHPZ22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KilgourGHJWT22,
  author       = {Kevin Kilgour and
                  Beat Gfeller and
                  Qingqing Huang and
                  Aren Jansen and
                  Scott Wisdom and
                  Marco Tagliasacchi},
  editor       = {Hanseok Ko and
                  John H. L. Hansen},
  title        = {Text-Driven Separation of Arbitrary Sounds},
  booktitle    = {Interspeech 2022, 23rd Annual Conference of the International Speech
                  Communication Association, Incheon, Korea, 18-22 September 2022},
  pages        = {5403--5407},
  publisher    = {{ISCA}},
  year         = {2022},
  url          = {https://doi.org/10.21437/Interspeech.2022-11052},
  doi          = {10.21437/INTERSPEECH.2022-11052},
  timestamp    = {Wed, 21 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/KilgourGHJWT22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ismir/HuangJLGLE22,
  author       = {Qingqing Huang and
                  Aren Jansen and
                  Joonseok Lee and
                  Ravi Ganti and
                  Judith Yue Li and
                  Daniel P. W. Ellis},
  editor       = {Preeti Rao and
                  Hema A. Murthy and
                  Ajay Srinivasamurthy and
                  Rachel M. Bittner and
                  Rafael Caro Repetto and
                  Masataka Goto and
                  Xavier Serra and
                  Marius Miron},
  title        = {MuLan: {A} Joint Embedding of Music Audio and Natural Language},
  booktitle    = {Proceedings of the 23rd International Society for Music Information
                  Retrieval Conference, {ISMIR} 2022, Bengaluru, India, December 4-8,
                  2022},
  pages        = {559--566},
  year         = {2022},
  url          = {https://archives.ismir.net/ismir2022/paper/000067.pdf},
  timestamp    = {Mon, 08 May 2023 14:44:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ismir/HuangJLGLE22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-05738,
  author       = {Kevin Kilgour and
                  Beat Gfeller and
                  Qingqing Huang and
                  Aren Jansen and
                  Scott Wisdom and
                  Marco Tagliasacchi},
  title        = {Text-Driven Separation of Arbitrary Sounds},
  journal      = {CoRR},
  volume       = {abs/2204.05738},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2204.05738},
  doi          = {10.48550/ARXIV.2204.05738},
  eprinttype    = {arXiv},
  eprint       = {2204.05738},
  timestamp    = {Wed, 20 Apr 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2204-05738.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2208-12415,
  author       = {Qingqing Huang and
                  Aren Jansen and
                  Joonseok Lee and
                  Ravi Ganti and
                  Judith Yue Li and
                  Daniel P. W. Ellis},
  title        = {MuLan: {A} Joint Embedding of Music Audio and Natural Language},
  journal      = {CoRR},
  volume       = {abs/2208.12415},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2208.12415},
  doi          = {10.48550/ARXIV.2208.12415},
  eprinttype    = {arXiv},
  eprint       = {2208.12415},
  timestamp    = {Mon, 29 Aug 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2208-12415.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HersheyEFJLMP21,
  author       = {Shawn Hershey and
                  Daniel P. W. Ellis and
                  Eduardo Fonseca and
                  Aren Jansen and
                  Caroline Liu and
                  R. Channing Moore and
                  Manoj Plakal},
  title        = {The Benefit of Temporally-Strong Labels in Audio Event Classification},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  pages        = {366--370},
  publisher    = {{IEEE}},
  year         = {2021},
  url          = {https://doi.org/10.1109/ICASSP39728.2021.9414579},
  doi          = {10.1109/ICASSP39728.2021.9414579},
  timestamp    = {Thu, 08 Jul 2021 17:12:48 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/HersheyEFJLMP21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/TzinisWJHREH21,
  author       = {Efthymios Tzinis and
                  Scott Wisdom and
                  Aren Jansen and
                  Shawn Hershey and
                  Tal Remez and
                  Dan Ellis and
                  John R. Hershey},
  title        = {Into the Wild with AudioScope: Unsupervised Audio-Visual Separation
                  of On-Screen Sounds},
  booktitle    = {9th International Conference on Learning Representations, {ICLR} 2021,
                  Virtual Event, Austria, May 3-7, 2021},
  publisher    = {OpenReview.net},
  year         = {2021},
  url          = {https://openreview.net/forum?id=MDsQkFP1Aw},
  timestamp    = {Wed, 23 Jun 2021 17:36:39 +0200},
  biburl       = {https://dblp.org/rec/conf/iclr/TzinisWJHREH21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/NagraniYAJSS21,
  author       = {Arsha Nagrani and
                  Shan Yang and
                  Anurag Arnab and
                  Aren Jansen and
                  Cordelia Schmid and
                  Chen Sun},
  editor       = {Marc'Aurelio Ranzato and
                  Alina Beygelzimer and
                  Yann N. Dauphin and
                  Percy Liang and
                  Jennifer Wortman Vaughan},
  title        = {Attention Bottlenecks for Multimodal Fusion},
  booktitle    = {Advances in Neural Information Processing Systems 34: Annual Conference
                  on Neural Information Processing Systems 2021, NeurIPS 2021, December
                  6-14, 2021, virtual},
  pages        = {14200--14213},
  year         = {2021},
  url          = {https://proceedings.neurips.cc/paper/2021/hash/76ba9f564ebbc35b1014ac498fafadd0-Abstract.html},
  timestamp    = {Tue, 03 May 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/nips/NagraniYAJSS21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/waspaa/WisdomJWEH21,
  author       = {Scott Wisdom and
                  Aren Jansen and
                  Ron J. Weiss and
                  Hakan Erdogan and
                  John R. Hershey},
  title        = {Sparse, Efficient, and Semantic Mixture Invariant Training: Taming
                  In-the-Wild Unsupervised Sound Separation},
  booktitle    = {{IEEE} Workshop on Applications of Signal Processing to Audio and
                  Acoustics, {WASPAA} 2021, New Paltz, NY, USA, October 17-20, 2021},
  pages        = {51--55},
  publisher    = {{IEEE}},
  year         = {2021},
  url          = {https://doi.org/10.1109/WASPAA52581.2021.9632714},
  doi          = {10.1109/WASPAA52581.2021.9632714},
  timestamp    = {Tue, 21 Dec 2021 10:11:15 +0100},
  biburl       = {https://dblp.org/rec/conf/waspaa/WisdomJWEH21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/waspaa/FonsecaJEWTHPHM21,
  author       = {Eduardo Fonseca and
                  Aren Jansen and
                  Daniel P. W. Ellis and
                  Scott Wisdom and
                  Marco Tagliasacchi and
                  John R. Hershey and
                  Manoj Plakal and
                  Shawn Hershey and
                  R. Channing Moore and
                  Xavier Serra},
  title        = {Self-Supervised Learning from Automatically Separated Sound Scenes},
  booktitle    = {{IEEE} Workshop on Applications of Signal Processing to Audio and
                  Acoustics, {WASPAA} 2021, New Paltz, NY, USA, October 17-20, 2021},
  pages        = {251--255},
  publisher    = {{IEEE}},
  year         = {2021},
  url          = {https://doi.org/10.1109/WASPAA52581.2021.9632739},
  doi          = {10.1109/WASPAA52581.2021.9632739},
  timestamp    = {Tue, 21 Dec 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/waspaa/FonsecaJEWTHPHM21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2105-02132,
  author       = {Eduardo Fonseca and
                  Aren Jansen and
                  Daniel P. W. Ellis and
                  Scott Wisdom and
                  Marco Tagliasacchi and
                  John R. Hershey and
                  Manoj Plakal and
                  Shawn Hershey and
                  R. Channing Moore and
                  Xavier Serra},
  title        = {Self-Supervised Learning from Automatically Separated Sound Scenes},
  journal      = {CoRR},
  volume       = {abs/2105.02132},
  year         = {2021},
  url          = {https://arxiv.org/abs/2105.02132},
  eprinttype    = {arXiv},
  eprint       = {2105.02132},
  timestamp    = {Wed, 12 May 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2105-02132.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2105-07031,
  author       = {Shawn Hershey and
                  Daniel P. W. Ellis and
                  Eduardo Fonseca and
                  Aren Jansen and
                  Caroline Liu and
                  R. Channing Moore and
                  Manoj Plakal},
  title        = {The Benefit Of Temporally-Strong Labels In Audio Event Classification},
  journal      = {CoRR},
  volume       = {abs/2105.07031},
  year         = {2021},
  url          = {https://arxiv.org/abs/2105.07031},
  eprinttype    = {arXiv},
  eprint       = {2105.07031},
  timestamp    = {Tue, 18 May 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2105-07031.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-00847,
  author       = {Scott Wisdom and
                  Aren Jansen and
                  Ron J. Weiss and
                  Hakan Erdogan and
                  John R. Hershey},
  title        = {Sparse, Efficient, and Semantic Mixture Invariant Training: Taming
                  In-the-Wild Unsupervised Sound Separation},
  journal      = {CoRR},
  volume       = {abs/2106.00847},
  year         = {2021},
  url          = {https://arxiv.org/abs/2106.00847},
  eprinttype    = {arXiv},
  eprint       = {2106.00847},
  timestamp    = {Fri, 11 Jun 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2106-00847.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2107-00135,
  author       = {Arsha Nagrani and
                  Shan Yang and
                  Anurag Arnab and
                  Aren Jansen and
                  Cordelia Schmid and
                  Chen Sun},
  title        = {Attention Bottlenecks for Multimodal Fusion},
  journal      = {CoRR},
  volume       = {abs/2107.00135},
  year         = {2021},
  url          = {https://arxiv.org/abs/2107.00135},
  eprinttype    = {arXiv},
  eprint       = {2107.00135},
  timestamp    = {Wed, 07 Jul 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2107-00135.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-13226,
  author       = {Yu Zhang and
                  Daniel S. Park and
                  Wei Han and
                  James Qin and
                  Anmol Gulati and
                  Joel Shor and
                  Aren Jansen and
                  Yuanzhong Xu and
                  Yanping Huang and
                  Shibo Wang and
                  Zongwei Zhou and
                  Bo Li and
                  Min Ma and
                  William Chan and
                  Jiahui Yu and
                  Yongqiang Wang and
                  Liangliang Cao and
                  Khe Chai Sim and
                  Bhuvana Ramabhadran and
                  Tara N. Sainath and
                  Fran{\c{c}}oise Beaufays and
                  Zhifeng Chen and
                  Quoc V. Le and
                  Chung{-}Cheng Chiu and
                  Ruoming Pang and
                  Yonghui Wu},
  title        = {BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning
                  for Automatic Speech Recognition},
  journal      = {CoRR},
  volume       = {abs/2109.13226},
  year         = {2021},
  url          = {https://arxiv.org/abs/2109.13226},
  eprinttype    = {arXiv},
  eprint       = {2109.13226},
  timestamp    = {Wed, 20 Jul 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2109-13226.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-04621,
  author       = {Joel Shor and
                  Aren Jansen and
                  Wei Han and
                  Daniel S. Park and
                  Yu Zhang},
  title        = {Universal Paralinguistic Speech Representations Using Self-Supervised
                  Conformers},
  journal      = {CoRR},
  volume       = {abs/2110.04621},
  year         = {2021},
  url          = {https://arxiv.org/abs/2110.04621},
  eprinttype    = {arXiv},
  eprint       = {2110.04621},
  timestamp    = {Thu, 21 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2110-04621.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spl/FonsecaHPEJM20,
  author       = {Eduardo Fonseca and
                  Shawn Hershey and
                  Manoj Plakal and
                  Daniel P. W. Ellis and
                  Aren Jansen and
                  R. Channing Moore},
  title        = {Addressing Missing Labels in Large-Scale Sound Event Recognition Using
                  a Teacher-Student Framework With Loss Masking},
  journal      = {{IEEE} Signal Process. Lett.},
  volume       = {27},
  pages        = {1235--1239},
  year         = {2020},
  url          = {https://doi.org/10.1109/LSP.2020.3006378},
  doi          = {10.1109/LSP.2020.3006378},
  timestamp    = {Thu, 27 Jul 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/spl/FonsecaHPEJM20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TzinisWHJE20,
  author       = {Efthymios Tzinis and
                  Scott Wisdom and
                  John R. Hershey and
                  Aren Jansen and
                  Daniel P. W. Ellis},
  title        = {Improving Universal Sound Separation Using Sound Classification},
  booktitle    = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
  pages        = {96--100},
  publisher    = {{IEEE}},
  year         = {2020},
  url          = {https://doi.org/10.1109/ICASSP40776.2020.9053921},
  doi          = {10.1109/ICASSP40776.2020.9053921},
  timestamp    = {Thu, 23 Jul 2020 16:19:28 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/TzinisWHJE20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/JansenEHMPPS20,
  author       = {Aren Jansen and
                  Daniel P. W. Ellis and
                  Shawn Hershey and
                  R. Channing Moore and
                  Manoj Plakal and
                  Ashok C. Popat and
                  Rif A. Saurous},
  title        = {Coincidence, Categorization, and Consolidation: Learning to Recognize
                  Sounds with Minimal Supervision},
  booktitle    = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
  pages        = {121--125},
  publisher    = {{IEEE}},
  year         = {2020},
  url          = {https://doi.org/10.1109/ICASSP40776.2020.9054137},
  doi          = {10.1109/ICASSP40776.2020.9054137},
  timestamp    = {Thu, 23 Jul 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/JansenEHMPPS20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HuangJZESA20,
  author       = {Qingqing Huang and
                  Aren Jansen and
                  Li Zhang and
                  Daniel P. W. Ellis and
                  Rif A. Saurous and
                  John R. Anderson},
  title        = {Large-Scale Weakly-Supervised Content Embeddings for Music Recommendation
                  and Tagging},
  booktitle    = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
  pages        = {8364--8368},
  publisher    = {{IEEE}},
  year         = {2020},
  url          = {https://doi.org/10.1109/ICASSP40776.2020.9053240},
  doi          = {10.1109/ICASSP40776.2020.9053240},
  timestamp    = {Tue, 11 Apr 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/HuangJZESA20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ShorJMLTQTSEH20,
  author       = {Joel Shor and
                  Aren Jansen and
                  Ronnie Maor and
                  Oran Lang and
                  Omry Tuval and
                  F{\'{e}}lix de Chaumont Quitry and
                  Marco Tagliasacchi and
                  Ira Shavitt and
                  Dotan Emanuel and
                  Yinnon Haviv},
  editor       = {Helen Meng and
                  Bo Xu and
                  Thomas Fang Zheng},
  title        = {Towards Learning a Universal Non-Semantic Representation of Speech},
  booktitle    = {Interspeech 2020, 21st Annual Conference of the International Speech
                  Communication Association, Virtual Event, Shanghai, China, 25-29 October
                  2020},
  pages        = {140--144},
  publisher    = {{ISCA}},
  year         = {2020},
  url          = {https://doi.org/10.21437/Interspeech.2020-1242},
  doi          = {10.21437/INTERSPEECH.2020-1242},
  timestamp    = {Fri, 29 Jan 2021 17:40:16 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/ShorJMLTQTSEH20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ismir/PatwariKWGCJ20,
  author       = {Ayush Patwari and
                  Nicholas Kong and
                  Jun Wang and
                  Ullas Gargi and
                  Michele Covell and
                  Aren Jansen},
  editor       = {Julie Cumming and
                  Jin Ha Lee and
                  Brian McFee and
                  Markus Schedl and
                  Johanna Devaney and
                  Cory McKay and
                  Eva Zangerle and
                  Timothy de Reuse},
  title        = {Semantically Meaningful Attributes from Co-Listen Embeddings for Playlist
                  Exploration and Expansion},
  booktitle    = {Proceedings of the 21th International Society for Music Information
                  Retrieval Conference, {ISMIR} 2020, Montreal, Canada, October 11-16,
                  2020},
  pages        = {527--533},
  year         = {2020},
  url          = {http://archives.ismir.net/ismir2020/paper/000125.pdf},
  timestamp    = {Mon, 19 Jul 2021 15:30:03 +0200},
  biburl       = {https://dblp.org/rec/conf/ismir/PatwariKWGCJ20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-12764,
  author       = {Joel Shor and
                  Aren Jansen and
                  Ronnie Maor and
                  Oran Lang and
                  Omry Tuval and
                  Felix de Chaumont Quitry and
                  Marco Tagliasacchi and
                  Ira Shavitt and
                  Dotan Emanuel and
                  Yinnon Haviv},
  title        = {Towards Learning a Universal Non-Semantic Representation of Speech},
  journal      = {CoRR},
  volume       = {abs/2002.12764},
  year         = {2020},
  url          = {https://arxiv.org/abs/2002.12764},
  eprinttype    = {arXiv},
  eprint       = {2002.12764},
  timestamp    = {Tue, 05 May 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2002-12764.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-00878,
  author       = {Eduardo Fonseca and
                  Shawn Hershey and
                  Manoj Plakal and
                  Daniel P. W. Ellis and
                  Aren Jansen and
                  R. Channing Moore and
                  Xavier Serra},
  title        = {Addressing Missing Labels in Large-scale Sound Event Recognition using
                  a Teacher-student Framework with Loss Masking},
  journal      = {CoRR},
  volume       = {abs/2005.00878},
  year         = {2020},
  url          = {https://arxiv.org/abs/2005.00878},
  eprinttype    = {arXiv},
  eprint       = {2005.00878},
  timestamp    = {Fri, 08 May 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2005-00878.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-01143,
  author       = {Efthymios Tzinis and
                  Scott Wisdom and
                  Aren Jansen and
                  Shawn Hershey and
                  Tal Remez and
                  Daniel P. W. Ellis and
                  John R. Hershey},
  title        = {Into the Wild with AudioScope: Unsupervised Audio-Visual Separation
                  of On-Screen Sounds},
  journal      = {CoRR},
  volume       = {abs/2011.01143},
  year         = {2020},
  url          = {https://arxiv.org/abs/2011.01143},
  eprinttype    = {arXiv},
  eprint       = {2011.01143},
  timestamp    = {Fri, 06 Nov 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2011-01143.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-05894,
  author       = {Aren Jansen and
                  Daniel P. W. Ellis and
                  Shawn Hershey and
                  R. Channing Moore and
                  Manoj Plakal and
                  Ashok C. Popat and
                  Rif A. Saurous},
  title        = {Coincidence, Categorization, and Consolidation: Learning to Recognize
                  Sounds with Minimal Supervision},
  journal      = {CoRR},
  volume       = {abs/1911.05894},
  year         = {2019},
  url          = {http://arxiv.org/abs/1911.05894},
  eprinttype    = {arXiv},
  eprint       = {1911.05894},
  timestamp    = {Mon, 02 Dec 2019 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1911-05894.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-07951,
  author       = {Efthymios Tzinis and
                  Scott Wisdom and
                  John R. Hershey and
                  Aren Jansen and
                  Daniel P. W. Ellis},
  title        = {Improving Universal Sound Separation Using Sound Classification},
  journal      = {CoRR},
  volume       = {abs/1911.07951},
  year         = {2019},
  url          = {http://arxiv.org/abs/1911.07951},
  eprinttype    = {arXiv},
  eprint       = {1911.07951},
  timestamp    = {Mon, 02 Dec 2019 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1911-07951.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/JansenPPEHLMS18,
  author       = {Aren Jansen and
                  Manoj Plakal and
                  Ratheet Pandya and
                  Daniel P. W. Ellis and
                  Shawn Hershey and
                  Jiayang Liu and
                  R. Channing Moore and
                  Rif A. Saurous},
  title        = {Unsupervised Learning of Semantic Audio Representations},
  booktitle    = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  pages        = {126--130},
  publisher    = {{IEEE}},
  year         = {2018},
  url          = {https://doi.org/10.1109/ICASSP.2018.8461684},
  doi          = {10.1109/ICASSP.2018.8461684},
  timestamp    = {Wed, 16 Oct 2019 14:14:52 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/JansenPPEHLMS18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csl/KamperJG17,
  author       = {Herman Kamper and
                  Aren Jansen and
                  Sharon Goldwater},
  title        = {A segmental framework for fully-unsupervised large-vocabulary speech
                  recognition},
  journal      = {Comput. Speech Lang.},
  volume       = {46},
  pages        = {154--174},
  year         = {2017},
  url          = {https://doi.org/10.1016/j.csl.2017.04.008},
  doi          = {10.1016/J.CSL.2017.04.008},
  timestamp    = {Mon, 28 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/csl/KamperJG17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/prl/JansenSL17,
  author       = {Aren Jansen and
                  Gregory Sell and
                  Vince Lyzinski},
  title        = {Scalable out-of-sample extension of graph embeddings using deep neural
                  networks},
  journal      = {Pattern Recognit. Lett.},
  volume       = {94},
  pages        = {1--6},
  year         = {2017},
  url          = {https://doi.org/10.1016/j.patrec.2017.04.016},
  doi          = {10.1016/J.PATREC.2017.04.016},
  timestamp    = {Sat, 22 Feb 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/prl/JansenSL17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tacl/RichterFSJ17,
  author       = {Caitlin Richter and
                  Naomi H. Feldman and
                  Harini Salgado and
                  Aren Jansen},
  title        = {Evaluating Low-Level Speech Features Against Human Perceptual Data},
  journal      = {Trans. Assoc. Comput. Linguistics},
  volume       = {5},
  pages        = {425--440},
  year         = {2017},
  url          = {https://doi.org/10.1162/tacl\_a\_00071},
  doi          = {10.1162/TACL\_A\_00071},
  timestamp    = {Thu, 23 Jun 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tacl/RichterFSJ17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HersheyCEGJMPPS17,
  author       = {Shawn Hershey and
                  Sourish Chaudhuri and
                  Daniel P. W. Ellis and
                  Jort F. Gemmeke and
                  Aren Jansen and
                  R. Channing Moore and
                  Manoj Plakal and
                  Devin Platt and
                  Rif A. Saurous and
                  Bryan Seybold and
                  Malcolm Slaney and
                  Ron J. Weiss and
                  Kevin W. Wilson},
  title        = {{CNN} architectures for large-scale audio classification},
  booktitle    = {2017 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
  pages        = {131--135},
  publisher    = {{IEEE}},
  year         = {2017},
  url          = {https://doi.org/10.1109/ICASSP.2017.7952132},
  doi          = {10.1109/ICASSP.2017.7952132},
  timestamp    = {Sun, 02 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/HersheyCEGJMPPS17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/GemmekeEFJLMPR17,
  author       = {Jort F. Gemmeke and
                  Daniel P. W. Ellis and
                  Dylan Freedman and
                  Aren Jansen and
                  Wade Lawrence and
                  R. Channing Moore and
                  Manoj Plakal and
                  Marvin Ritter},
  title        = {Audio Set: An ontology and human-labeled dataset for audio events},
  booktitle    = {2017 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
  pages        = {776--780},
  publisher    = {{IEEE}},
  year         = {2017},
  url          = {https://doi.org/10.1109/ICASSP.2017.7952261},
  doi          = {10.1109/ICASSP.2017.7952261},
  timestamp    = {Sun, 02 Jun 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/GemmekeEFJLMPR17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/JansenGELLF17,
  author       = {Aren Jansen and
                  Jort F. Gemmeke and
                  Daniel P. W. Ellis and
                  Xiaofeng Liu and
                  Wade Lawrence and
                  Dylan Freedman},
  title        = {Large-scale audio event discovery in one million YouTube videos},
  booktitle    = {2017 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
  pages        = {786--790},
  publisher    = {{IEEE}},
  year         = {2017},
  url          = {https://doi.org/10.1109/ICASSP.2017.7952263},
  doi          = {10.1109/ICASSP.2017.7952263},
  timestamp    = {Fri, 23 Jun 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/JansenGELLF17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1711-02209,
  author       = {Aren Jansen and
                  Manoj Plakal and
                  Ratheet Pandya and
                  Daniel P. W. Ellis and
                  Shawn Hershey and
                  Jiayang Liu and
                  R. Channing Moore and
                  Rif A. Saurous},
  title        = {Unsupervised Learning of Semantic Audio Representations},
  journal      = {CoRR},
  volume       = {abs/1711.02209},
  year         = {2017},
  url          = {http://arxiv.org/abs/1711.02209},
  eprinttype    = {arXiv},
  eprint       = {1711.02209},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1711-02209.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/KamperJG16,
  author       = {Herman Kamper and
                  Aren Jansen and
                  Sharon Goldwater},
  title        = {Unsupervised Word Segmentation and Lexicon Discovery Using Acoustic
                  Word Embeddings},
  journal      = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  volume       = {24},
  number       = {4},
  pages        = {669--679},
  year         = {2016},
  url          = {https://doi.org/10.1109/TASLP.2016.2517567},
  doi          = {10.1109/TASLP.2016.2517567},
  timestamp    = {Thu, 14 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/taslp/KamperJG16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cogsci/RichterFSJ16,
  author       = {Caitlin Richter and
                  Naomi Feldman and
                  Harini Salgado and
                  Aren Jansen},
  editor       = {Anna Papafragou and
                  Daniel Grodner and
                  Daniel Mirman and
                  John C. Trueswell},
  title        = {A Framework for Evaluating Speech Representations},
  booktitle    = {Proceedings of the 38th Annual Meeting of the Cognitive Science Society,
                  Recogbizing and Representing Events, CogSci 2016, Philadelphia, PA,
                  USA, August 10-13, 2016},
  publisher    = {cognitivesciencesociety.org},
  year         = {2016},
  url          = {https://mindmodeling.org/cogsci2016/papers/0335/index.html},
  timestamp    = {Tue, 02 Feb 2021 08:04:15 +0100},
  biburl       = {https://dblp.org/rec/conf/cogsci/RichterFSJ16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiuJK16,
  author       = {Chunxi Liu and
                  Aren Jansen and
                  Sanjeev Khudanpur},
  title        = {Context-dependent point process models for keyword search and detection-based
                  {ASR}},
  booktitle    = {2016 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
  pages        = {6025--6029},
  publisher    = {{IEEE}},
  year         = {2016},
  url          = {https://doi.org/10.1109/ICASSP.2016.7472834},
  doi          = {10.1109/ICASSP.2016.7472834},
  timestamp    = {Wed, 16 Oct 2019 14:14:52 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/LiuJK16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sltu/VersteeghAJD16,
  author       = {Maarten Versteegh and
                  Xavier Anguera and
                  Aren Jansen and
                  Emmanuel Dupoux},
  editor       = {Sakriani Sakti and
                  Mirna Adriani and
                  Ayu Purwarianti and
                  Laurent Besacier and
                  Eric Castelli and
                  Pascal Nocera},
  title        = {The Zero Resource Speech Challenge 2015: Proposed Approaches and Results},
  booktitle    = {SLTU-2016, 5th Workshop on Spoken Language Technologies for Under-resourced
                  languages, 9-12 May 2016, Yogyakarta, Indonesia},
  series       = {Procedia Computer Science},
  volume       = {81},
  pages        = {67--72},
  publisher    = {Elsevier},
  year         = {2016},
  url          = {https://doi.org/10.1016/j.procs.2016.04.031},
  doi          = {10.1016/J.PROCS.2016.04.031},
  timestamp    = {Wed, 23 Mar 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sltu/VersteeghAJD16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KamperJG16,
  author       = {Herman Kamper and
                  Aren Jansen and
                  Sharon Goldwater},
  title        = {Unsupervised word segmentation and lexicon discovery using acoustic
                  word embeddings},
  journal      = {CoRR},
  volume       = {abs/1603.02845},
  year         = {2016},
  url          = {http://arxiv.org/abs/1603.02845},
  eprinttype    = {arXiv},
  eprint       = {1603.02845},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/KamperJG16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KamperJG16a,
  author       = {Herman Kamper and
                  Aren Jansen and
                  Sharon Goldwater},
  title        = {A segmental framework for fully-unsupervised large-vocabulary speech
                  recognition},
  journal      = {CoRR},
  volume       = {abs/1606.06950},
  year         = {2016},
  url          = {http://arxiv.org/abs/1606.06950},
  eprinttype    = {arXiv},
  eprint       = {1606.06950},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/KamperJG16a.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HersheyCEGJMPPS16,
  author       = {Shawn Hershey and
                  Sourish Chaudhuri and
                  Daniel P. W. Ellis and
                  Jort F. Gemmeke and
                  Aren Jansen and
                  R. Channing Moore and
                  Manoj Plakal and
                  Devin Platt and
                  Rif A. Saurous and
                  Bryan Seybold and
                  Malcolm Slaney and
                  Ron J. Weiss and
                  Kevin W. Wilson},
  title        = {{CNN} Architectures for Large-Scale Audio Classification},
  journal      = {CoRR},
  volume       = {abs/1609.09430},
  year         = {2016},
  url          = {http://arxiv.org/abs/1609.09430},
  eprinttype    = {arXiv},
  eprint       = {1609.09430},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/HersheyCEGJMPPS16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WintrodeSJFGM15,
  author       = {Jonathan Wintrode and
                  Gregory Sell and
                  Aren Jansen and
                  Michelle Fox and
                  Daniel Garcia{-}Romero and
                  Alan McCree},
  title        = {Content-based recommender systems for spoken documents},
  booktitle    = {2015 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia,
                  April 19-24, 2015},
  pages        = {5201--5205},
  publisher    = {{IEEE}},
  year         = {2015},
  url          = {https://doi.org/10.1109/ICASSP.2015.7178963},
  doi          = {10.1109/ICASSP.2015.7178963},
  timestamp    = {Wed, 16 Oct 2019 14:14:52 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/WintrodeSJFGM15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KamperEJG15,
  author       = {Herman Kamper and
                  Micha Elsner and
                  Aren Jansen and
                  Sharon Goldwater},
  title        = {Unsupervised neural network based feature extraction using weak top-down
                  constraints},
  booktitle    = {2015 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia,
                  April 19-24, 2015},
  pages        = {5818--5822},
  publisher    = {{IEEE}},
  year         = {2015},
  url          = {https://doi.org/10.1109/ICASSP.2015.7179087},
  doi          = {10.1109/ICASSP.2015.7179087},
  timestamp    = {Thu, 14 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/KamperEJG15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LevinJD15,
  author       = {Keith D. Levin and
                  Aren Jansen and
                  Benjamin Van Durme},
  title        = {Segmental acoustic indexing for zero resource keyword search},
  booktitle    = {2015 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia,
                  April 19-24, 2015},
  pages        = {5828--5832},
  publisher    = {{IEEE}},
  year         = {2015},
  url          = {https://doi.org/10.1109/ICASSP.2015.7179089},
  doi          = {10.1109/ICASSP.2015.7179089},
  timestamp    = {Mon, 31 Jan 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icassp/LevinJD15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KamperJG15,
  author       = {Herman Kamper and
                  Aren Jansen and
                  Sharon Goldwater},
  title        = {Fully unsupervised small-vocabulary speech recognition using a segmental
                  Bayesian model},
  booktitle    = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech
                  Communication Association, Dresden, Germany, September 6-10, 2015},
  pages        = {678--682},
  publisher    = {{ISCA}},
  year         = {2015},
  url          = {https://doi.org/10.21437/Interspeech.2015-239},
  doi          = {10.21437/INTERSPEECH.2015-239},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/KamperJG15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/VersteeghTSCAJD15,
  author       = {Maarten Versteegh and
                  Roland Thiolli{\`{e}}re and
                  Thomas Schatz and
                  Xuan{-}Nga Cao and
                  Xavier Anguera and
                  Aren Jansen and
                  Emmanuel Dupoux},
  title        = {The zero resource speech challenge 2015},
  booktitle    = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech
                  Communication Association, Dresden, Germany, September 6-10, 2015},
  pages        = {3169--3173},
  publisher    = {{ISCA}},
  year         = {2015},
  url          = {https://doi.org/10.21437/Interspeech.2015-638},
  doi          = {10.21437/INTERSPEECH.2015-638},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/VersteeghTSCAJD15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/RenshawKJG15,
  author       = {Daniel Renshaw and
                  Herman Kamper and
                  Aren Jansen and
                  Sharon Goldwater},
  title        = {A comparison of neural network methods for unsupervised representation
                  learning on the zero resource speech challenge},
  booktitle    = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech
                  Communication Association, Dresden, Germany, September 6-10, 2015},
  pages        = {3199--3203},
  publisher    = {{ISCA}},
  year         = {2015},
  url          = {https://doi.org/10.21437/Interspeech.2015-644},
  doi          = {10.21437/INTERSPEECH.2015-644},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/RenshawKJG15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LyzinskiSJ15,
  author       = {Vince Lyzinski and
                  Gregory Sell and
                  Aren Jansen},
  title        = {An evaluation of graph clustering methods for unsupervised term discovery},
  booktitle    = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech
                  Communication Association, Dresden, Germany, September 6-10, 2015},
  pages        = {3209--3213},
  publisher    = {{ISCA}},
  year         = {2015},
  url          = {https://doi.org/10.21437/Interspeech.2015-646},
  doi          = {10.21437/INTERSPEECH.2015-646},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/LyzinskiSJ15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/naacl/WhiteOJPS15,
  author       = {Jerome White and
                  Douglas W. Oard and
                  Aren Jansen and
                  Jiaul H. Paik and
                  Rashmi Sankepally},
  editor       = {Rada Mihalcea and
                  Joyce Yue Chai and
                  Anoop Sarkar},
  title        = {Using Zero-Resource Spoken Term Discovery for Ranked Retrieval},
  booktitle    = {{NAACL} {HLT} 2015, The 2015 Conference of the North American Chapter
                  of the Association for Computational Linguistics: Human Language Technologies,
                  Denver, Colorado, USA, May 31 - June 5, 2015},
  pages        = {588--597},
  publisher    = {The Association for Computational Linguistics},
  year         = {2015},
  url          = {https://doi.org/10.3115/v1/n15-1061},
  doi          = {10.3115/V1/N15-1061},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/naacl/WhiteOJPS15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigir/OardSWJH15,
  author       = {Douglas W. Oard and
                  Rashmi Sankepally and
                  Jerome White and
                  Aren Jansen and
                  Craig Harman},
  editor       = {Ricardo Baeza{-}Yates and
                  Mounia Lalmas and
                  Alistair Moffat and
                  Berthier A. Ribeiro{-}Neto},
  title        = {A Test Collection for Spoken Gujarati Queries},
  booktitle    = {Proceedings of the 38th International {ACM} {SIGIR} Conference on
                  Research and Development in Information Retrieval, Santiago, Chile,
                  August 9-13, 2015},
  pages        = {919--922},
  publisher    = {{ACM}},
  year         = {2015},
  url          = {https://doi.org/10.1145/2766462.2767791},
  doi          = {10.1145/2766462.2767791},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/sigir/OardSWJH15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/JansenSL15,
  author       = {Aren Jansen and
                  Gregory Sell and
                  Vince Lyzinski},
  title        = {Scalable Out-of-Sample Extension of Graph Embeddings Using Deep Neural
                  Networks},
  journal      = {CoRR},
  volume       = {abs/1508.04422},
  year         = {2015},
  url          = {http://arxiv.org/abs/1508.04422},
  eprinttype    = {arXiv},
  eprint       = {1508.04422},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/JansenSL15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/JansenGCH14,
  author       = {Aren Jansen and
                  Daniel Garcia{-}Romero and
                  Pascal Clark and
                  Jaime Hernandez{-}Cordero},
  title        = {Unsupervised idiolect discovery for speaker recognition},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2014, Florence, Italy, May 4-9, 2014},
  pages        = {1675--1679},
  publisher    = {{IEEE}},
  year         = {2014},
  url          = {https://doi.org/10.1109/ICASSP.2014.6853883},
  doi          = {10.1109/ICASSP.2014.6853883},
  timestamp    = {Thu, 14 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/JansenGCH14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KintzleyJH14,
  author       = {Keith Kintzley and
                  Aren Jansen and
                  Hynek Hermansky},
  title        = {Featherweight phonetic keyword search for conversational speech},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2014, Florence, Italy, May 4-9, 2014},
  pages        = {7859--7863},
  publisher    = {{IEEE}},
  year         = {2014},
  url          = {https://doi.org/10.1109/ICASSP.2014.6855130},
  doi          = {10.1109/ICASSP.2014.6855130},
  timestamp    = {Fri, 19 May 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/KintzleyJH14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiuJCKTK14,
  author       = {Chunxi Liu and
                  Aren Jansen and
                  Guoguo Chen and
                  Keith Kintzley and
                  Jan Trmal and
                  Sanjeev Khudanpur},
  editor       = {Haizhou Li and
                  Helen M. Meng and
                  Bin Ma and
                  Engsiong Chng and
                  Lei Xie},
  title        = {Low-resource open vocabulary keyword search using point process models},
  booktitle    = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech
                  Communication Association, Singapore, September 14-18, 2014},
  pages        = {2789--2793},
  publisher    = {{ISCA}},
  year         = {2014},
  url          = {https://doi.org/10.21437/Interspeech.2014-533},
  doi          = {10.21437/INTERSPEECH.2014-533},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/LiuJCKTK14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/lrec/LudusanVJGCJD14,
  author       = {Bogdan Ludusan and
                  Maarten Versteegh and
                  Aren Jansen and
                  Guillaume Gravier and
                  Xuan{-}Nga Cao and
                  Mark Johnson and
                  Emmanuel Dupoux},
  editor       = {Nicoletta Calzolari and
                  Khalid Choukri and
                  Thierry Declerck and
                  Hrafn Loftsson and
                  Bente Maegaard and
                  Joseph Mariani and
                  Asunci{\'{o}}n Moreno and
                  Jan Odijk and
                  Stelios Piperidis},
  title        = {Bridging the gap between speech technology and natural language processing:
                  an evaluation toolbox for term discovery systems},
  booktitle    = {Proceedings of the Ninth International Conference on Language Resources
                  and Evaluation, {LREC} 2014, Reykjavik, Iceland, May 26-31, 2014},
  pages        = {560--567},
  publisher    = {European Language Resources Association {(ELRA)}},
  year         = {2014},
  url          = {http://www.lrec-conf.org/proceedings/lrec2014/summaries/320.html},
  timestamp    = {Mon, 19 Aug 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/lrec/LudusanVJGCJD14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/KamperJKG14,
  author       = {Herman Kamper and
                  Aren Jansen and
                  Simon King and
                  Sharon Goldwater},
  title        = {Unsupervised lexical clustering of speech segments using fixed-dimensional
                  acoustic embeddings},
  booktitle    = {2014 {IEEE} Spoken Language Technology Workshop, {SLT} 2014, South
                  Lake Tahoe, NV, USA, December 7-10, 2014},
  pages        = {100--105},
  publisher    = {{IEEE}},
  year         = {2014},
  url          = {https://doi.org/10.1109/SLT.2014.7078557},
  doi          = {10.1109/SLT.2014.7078557},
  timestamp    = {Mon, 29 Jan 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/slt/KamperJKG14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/TrmalCPKGZMLJKY14,
  author       = {Jan Trmal and
                  Guoguo Chen and
                  Daniel Povey and
                  Sanjeev Khudanpur and
                  Pegah Ghahremani and
                  Xiaohui Zhang and
                  Vimal Manohar and
                  Chunxi Liu and
                  Aren Jansen and
                  Dietrich Klakow and
                  David Yarowsky and
                  Florian Metze},
  title        = {A keyword search system using open source software},
  booktitle    = {2014 {IEEE} Spoken Language Technology Workshop, {SLT} 2014, South
                  Lake Tahoe, NV, USA, December 7-10, 2014},
  pages        = {530--535},
  publisher    = {{IEEE}},
  year         = {2014},
  url          = {https://doi.org/10.1109/SLT.2014.7078630},
  doi          = {10.1109/SLT.2014.7078630},
  timestamp    = {Wed, 24 May 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/slt/TrmalCPKGZMLJKY14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsp/JansenN13,
  author       = {Aren Jansen and
                  Partha Niyogi},
  title        = {Intrinsic Spectral Analysis},
  journal      = {{IEEE} Trans. Signal Process.},
  volume       = {61},
  number       = {7},
  pages        = {1698--1710},
  year         = {2013},
  url          = {https://doi.org/10.1109/TSP.2013.2238931},
  doi          = {10.1109/TSP.2013.2238931},
  timestamp    = {Tue, 10 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/tsp/JansenN13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/LevinHJL13,
  author       = {Keith D. Levin and
                  Katharine Henry and
                  Aren Jansen and
                  Karen Livescu},
  title        = {Fixed-dimensional acoustic embeddings of variable-length segments
                  in low-resource settings},
  booktitle    = {2013 {IEEE} Workshop on Automatic Speech Recognition and Understanding,
                  Olomouc, Czech Republic, December 8-12, 2013},
  pages        = {410--415},
  publisher    = {{IEEE}},
  year         = {2013},
  url          = {https://doi.org/10.1109/ASRU.2013.6707765},
  doi          = {10.1109/ASRU.2013.6707765},
  timestamp    = {Mon, 31 Jan 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/asru/LevinHJL13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/fire/OardWPSJ13,
  author       = {Douglas W. Oard and
                  Jerome White and
                  Jiaul H. Paik and
                  Rashmi Sankepally and
                  Aren Jansen},
  editor       = {Prasenjit Majumder and
                  Mandar Mitra and
                  Madhulika Agrawal and
                  Parth Mehta},
  title        = {The {FIRE} 2013 Question Answering for the Spoken Web Task},
  booktitle    = {Proceedings of the 5th 2013 Forum on Information Retrieval Evaluation,
                  {FIRE} '13, New Delhi, India, December 4-6, 2013},
  pages        = {1:1--1:3},
  publisher    = {{ACM}},
  year         = {2013},
  url          = {https://doi.org/10.1145/2701336.2701638},
  doi          = {10.1145/2701336.2701638},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/fire/OardWPSJ13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ClarkMJH13,
  author       = {Pascal Clark and
                  Sri Harish Reddy Mallidi and
                  Aren Jansen and
                  Hynek Hermansky},
  title        = {Frequency offset correction in speech without detecting pitch},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
  pages        = {7020--7024},
  publisher    = {{IEEE}},
  year         = {2013},
  url          = {https://doi.org/10.1109/ICASSP.2013.6639023},
  doi          = {10.1109/ICASSP.2013.6639023},
  timestamp    = {Wed, 16 Oct 2019 14:14:52 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/ClarkMJH13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/JansenTH13,
  author       = {Aren Jansen and
                  Samuel Thomas and
                  Hynek Hermansky},
  title        = {Weak top-down constraints for unsupervised acoustic model training},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
  pages        = {8091--8095},
  publisher    = {{IEEE}},
  year         = {2013},
  url          = {https://doi.org/10.1109/ICASSP.2013.6639241},
  doi          = {10.1109/ICASSP.2013.6639241},
  timestamp    = {Fri, 03 Jul 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/JansenTH13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/JansenDGJKCFHMRSCMVBBCDFHLLNPRST13,
  author       = {Aren Jansen and
                  Emmanuel Dupoux and
                  Sharon Goldwater and
                  Mark Johnson and
                  Sanjeev Khudanpur and
                  Kenneth Church and
                  Naomi Feldman and
                  Hynek Hermansky and
                  Florian Metze and
                  Richard C. Rose and
                  Mike Seltzer and
                  Pascal Clark and
                  Ian McGraw and
                  Balakrishnan Varadarajan and
                  Erin Bennett and
                  Benjamin B{\"{o}}rschinger and
                  Justin T. Chiu and
                  Ewan Dunbar and
                  Abdellah Fourtassi and
                  David Harwath and
                  Chia{-}ying Lee and
                  Keith D. Levin and
                  Atta Norouzian and
                  Vijayaditya Peddinti and
                  Rachael Richardson and
                  Thomas Schatz and
                  Samuel Thomas},
  title        = {A summary of the 2012 {JHU} {CLSP} workshop on zero resource speech
                  technologies and models of early language acquisition},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
  pages        = {8111--8115},
  publisher    = {{IEEE}},
  year         = {2013},
  url          = {https://doi.org/10.1109/ICASSP.2013.6639245},
  doi          = {10.1109/ICASSP.2013.6639245},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/JansenDGJKCFHMRSCMVBBCDFHLLNPRST13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/NorouzianRGJ13,
  author       = {Atta Norouzian and
                  Richard C. Rose and
                  Sina Hamidi Ghalehjegh and
                  Aren Jansen},
  title        = {Zero resource graph-based confidence estimation for open vocabulary
                  spoken term detection},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013},
  pages        = {8292--8296},
  publisher    = {{IEEE}},
  year         = {2013},
  url          = {https://doi.org/10.1109/ICASSP.2013.6639282},
  doi          = {10.1109/ICASSP.2013.6639282},
  timestamp    = {Fri, 19 May 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/NorouzianRGJ13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KintzleyJH13,
  author       = {Keith Kintzley and
                  Aren Jansen and
                  Hynek Hermansky},
  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        = {Text-to-speech inspired duration modeling for improved whole-word
                  acoustic models},
  booktitle    = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech
                  Communication Association, Lyon, France, August 25-29, 2013},
  pages        = {1253--1257},
  publisher    = {{ISCA}},
  year         = {2013},
  url          = {https://doi.org/10.21437/Interspeech.2013-337},
  doi          = {10.21437/INTERSPEECH.2013-337},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/KintzleyJH13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SchatzPBJHD13,
  author       = {Thomas Schatz and
                  Vijayaditya Peddinti and
                  Francis R. Bach and
                  Aren Jansen and
                  Hynek Hermansky and
                  Emmanuel Dupoux},
  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        = {Evaluating speech features with the minimal-pair {ABX} task: analysis
                  of the classical {MFC/PLP} pipeline},
  booktitle    = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech
                  Communication Association, Lyon, France, August 25-29, 2013},
  pages        = {1781--1785},
  publisher    = {{ISCA}},
  year         = {2013},
  url          = {https://doi.org/10.21437/Interspeech.2013-441},
  doi          = {10.21437/INTERSPEECH.2013-441},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/SchatzPBJHD13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NorouzianRJ13,
  author       = {Atta Norouzian and
                  Richard C. Rose and
                  Aren Jansen},
  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        = {Semi-supervised manifold learning approaches for spoken term verification},
  booktitle    = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech
                  Communication Association, Lyon, France, August 25-29, 2013},
  pages        = {2594--2598},
  publisher    = {{ISCA}},
  year         = {2013},
  url          = {https://doi.org/10.21437/Interspeech.2013-583},
  doi          = {10.21437/INTERSPEECH.2013-583},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/NorouzianRJ13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KintzleyJH12,
  author       = {Keith Kintzley and
                  Aren Jansen and
                  Hynek Hermansky},
  title        = {{MAP} Estimation of Whole-Word Acoustic Models with Dictionary Priors},
  booktitle    = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
                  Communication Association, Portland, Oregon, USA, September 9-13,
                  2012},
  pages        = {787--790},
  publisher    = {{ISCA}},
  year         = {2012},
  url          = {https://doi.org/10.21437/Interspeech.2012-241},
  doi          = {10.21437/INTERSPEECH.2012-241},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/KintzleyJH12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ThomasGJH12,
  author       = {Samuel Thomas and
                  Sriram Ganapathy and
                  Aren Jansen and
                  Hynek Hermansky},
  title        = {Data-driven Posterior Features for Low Resource Speech Recognition
                  Applications},
  booktitle    = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
                  Communication Association, Portland, Oregon, USA, September 9-13,
                  2012},
  pages        = {791--794},
  publisher    = {{ISCA}},
  year         = {2012},
  url          = {https://doi.org/10.21437/Interspeech.2012-242},
  doi          = {10.21437/INTERSPEECH.2012-242},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/ThomasGJH12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/JansenTH12,
  author       = {Aren Jansen and
                  Samuel Thomas and
                  Hynek Hermansky},
  title        = {Intrinsic Spectral Analysis for Zero and High Resource Speech Recognition},
  booktitle    = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
                  Communication Association, Portland, Oregon, USA, September 9-13,
                  2012},
  pages        = {879--882},
  publisher    = {{ISCA}},
  year         = {2012},
  url          = {https://doi.org/10.21437/Interspeech.2012-266},
  doi          = {10.21437/INTERSPEECH.2012-266},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/JansenTH12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KintzleyJCH12,
  author       = {Keith Kintzley and
                  Aren Jansen and
                  Kenneth Church and
                  Hynek Hermansky},
  title        = {Inverting the Point Process Model for Fast Phonetic Keyword Search},
  booktitle    = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
                  Communication Association, Portland, Oregon, USA, September 9-13,
                  2012},
  pages        = {2438--2441},
  publisher    = {{ISCA}},
  year         = {2012},
  url          = {https://doi.org/10.21437/Interspeech.2012-638},
  doi          = {10.21437/INTERSPEECH.2012-638},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/KintzleyJCH12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NorouzianJRT12,
  author       = {Atta Norouzian and
                  Aren Jansen and
                  Richard C. Rose and
                  Samuel Thomas},
  title        = {Exploiting Discriminative Point Process Models for Spoken Term Detection},
  booktitle    = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
                  Communication Association, Portland, Oregon, USA, September 9-13,
                  2012},
  pages        = {2442--2445},
  publisher    = {{ISCA}},
  year         = {2012},
  url          = {https://doi.org/10.21437/Interspeech.2012-639},
  doi          = {10.21437/INTERSPEECH.2012-639},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/NorouzianJRT12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/JansenD12,
  author       = {Aren Jansen and
                  Benjamin Van Durme},
  title        = {Indexing Raw Acoustic Features for Scalable Zero Resource Search},
  booktitle    = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
                  Communication Association, Portland, Oregon, USA, September 9-13,
                  2012},
  pages        = {2466--2469},
  publisher    = {{ISCA}},
  year         = {2012},
  url          = {https://doi.org/10.21437/Interspeech.2012-566},
  doi          = {10.21437/INTERSPEECH.2012-566},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/JansenD12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mediaeval/JansenDC12,
  author       = {Aren Jansen and
                  Benjamin Van Durme and
                  Pascal Clark},
  editor       = {Martha A. Larson and
                  Sebastian Schmiedeke and
                  Pascal Kelm and
                  Adam Rae and
                  Vasileios Mezaris and
                  Tomas Piatrik and
                  Mohammad Soleymani and
                  Florian Metze and
                  Gareth J. F. Jones},
  title        = {The {JHU-HLTCOE} Spoken Web Search System for MediaEval 2012},
  booktitle    = {Working Notes Proceedings of the MediaEval 2012 Workshop, Santa Croce
                  in Fossabanda, Pisa, Italy, October 4-5, 2012},
  series       = {{CEUR} Workshop Proceedings},
  volume       = {927},
  publisher    = {CEUR-WS.org},
  year         = {2012},
  url          = {https://ceur-ws.org/Vol-927/mediaeval2012\_submission\_30.pdf},
  timestamp    = {Fri, 10 Mar 2023 16:22:12 +0100},
  biburl       = {https://dblp.org/rec/conf/mediaeval/JansenDC12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/JansenD11,
  author       = {Aren Jansen and
                  Benjamin Van Durme},
  editor       = {David Nahamoo and
                  Michael Picheny},
  title        = {Efficient spoken term discovery using randomized algorithms},
  booktitle    = {2011 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
                  {ASRU} 2011, Waikoloa, HI, USA, December 11-15, 2011},
  pages        = {401--406},
  publisher    = {{IEEE}},
  year         = {2011},
  url          = {https://doi.org/10.1109/ASRU.2011.6163965},
  doi          = {10.1109/ASRU.2011.6163965},
  timestamp    = {Wed, 16 Oct 2019 14:14:51 +0200},
  biburl       = {https://dblp.org/rec/conf/asru/JansenD11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/KarakosDCJK11,
  author       = {Damianos G. Karakos and
                  Mark Dredze and
                  Ken Ward Church and
                  Aren Jansen and
                  Sanjeev Khudanpur},
  editor       = {David Nahamoo and
                  Michael Picheny},
  title        = {Estimating document frequencies in a speech corpus},
  booktitle    = {2011 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
                  {ASRU} 2011, Waikoloa, HI, USA, December 11-15, 2011},
  pages        = {407--412},
  publisher    = {{IEEE}},
  year         = {2011},
  url          = {https://doi.org/10.1109/ASRU.2011.6163966},
  doi          = {10.1109/ASRU.2011.6163966},
  timestamp    = {Sun, 22 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/asru/KarakosDCJK11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ZweigNCDACSWSHKJTSBK11,
  author       = {Geoffrey Zweig and
                  Patrick Nguyen and
                  Dirk Van Compernolle and
                  Kris Demuynck and
                  Les E. Atlas and
                  Pascal Clark and
                  Gregory Sell and
                  Meihong Wang and
                  Fei Sha and
                  Hynek Hermansky and
                  Damianos G. Karakos and
                  Aren Jansen and
                  Samuel Thomas and
                  Sivaram G. S. V. S. and
                  Samuel R. Bowman and
                  Justine T. Kao},
  title        = {Speech recognitionwith segmental conditional random fields: {A} summary
                  of the {JHU} {CLSP} 2010 Summer Workshop},
  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        = {5044--5047},
  publisher    = {{IEEE}},
  year         = {2011},
  url          = {https://doi.org/10.1109/ICASSP.2011.5947490},
  doi          = {10.1109/ICASSP.2011.5947490},
  timestamp    = {Fri, 03 Jul 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/ZweigNCDACSWSHKJTSBK11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/Jansen11,
  author       = {Aren Jansen},
  title        = {Whole word discriminative point process models},
  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        = {5180--5183},
  publisher    = {{IEEE}},
  year         = {2011},
  url          = {https://doi.org/10.1109/ICASSP.2011.5947524},
  doi          = {10.1109/ICASSP.2011.5947524},
  timestamp    = {Fri, 19 May 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/Jansen11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/CarlinTJH11,
  author       = {Michael A. Carlin and
                  Samuel Thomas and
                  Aren Jansen and
                  Hynek Hermansky},
  title        = {Rapid Evaluation of Speech Representations for Spoken Term Discovery},
  booktitle    = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech
                  Communication Association, Florence, Italy, August 27-31, 2011},
  pages        = {821--824},
  publisher    = {{ISCA}},
  year         = {2011},
  url          = {https://doi.org/10.21437/Interspeech.2011-304},
  doi          = {10.21437/INTERSPEECH.2011-304},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/CarlinTJH11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/JansenC11,
  author       = {Aren Jansen and
                  Kenneth Church},
  title        = {Towards Unsupervised Training of Speaker Independent Acoustic Models},
  booktitle    = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech
                  Communication Association, Florence, Italy, August 27-31, 2011},
  pages        = {1693--1692},
  publisher    = {{ISCA}},
  year         = {2011},
  url          = {https://doi.org/10.21437/Interspeech.2011-184},
  doi          = {10.21437/INTERSPEECH.2011-184},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/JansenC11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KintzleyJH11,
  author       = {Keith Kintzley and
                  Aren Jansen and
                  Hynek Hermansky},
  title        = {Event Selection from Phone Posteriorgrams Using Matched Filters},
  booktitle    = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech
                  Communication Association, Florence, Italy, August 27-31, 2011},
  pages        = {1905--1908},
  publisher    = {{ISCA}},
  year         = {2011},
  url          = {https://doi.org/10.21437/Interspeech.2011-354},
  doi          = {10.21437/INTERSPEECH.2011-354},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/KintzleyJH11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/DredzeJCC10,
  author       = {Mark Dredze and
                  Aren Jansen and
                  Glen Coppersmith and
                  Ken Ward Church},
  title        = {{NLP} on Spoken Documents Without {ASR}},
  booktitle    = {Proceedings of the 2010 Conference on Empirical Methods in Natural
                  Language Processing, {EMNLP} 2010, 9-11 October 2010, {MIT} Stata
                  Center, Massachusetts, USA, {A} meeting of SIGDAT, a Special Interest
                  Group of the {ACL}},
  pages        = {460--470},
  publisher    = {{ACL}},
  year         = {2010},
  url          = {https://aclanthology.org/D10-1045/},
  timestamp    = {Fri, 06 Aug 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/emnlp/DredzeJCC10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/JansenN10,
  author       = {Aren Jansen and
                  Partha Niyogi},
  title        = {Detection-based speech recognition with sparse point process 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        = {4362--4365},
  publisher    = {{IEEE}},
  year         = {2010},
  url          = {https://doi.org/10.1109/ICASSP.2010.5495636},
  doi          = {10.1109/ICASSP.2010.5495636},
  timestamp    = {Fri, 19 May 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/JansenN10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/JansenCH10,
  author       = {Aren Jansen and
                  Kenneth Church and
                  Hynek Hermansky},
  editor       = {Takao Kobayashi and
                  Keikichi Hirose and
                  Satoshi Nakamura},
  title        = {Towards spoken term discovery at scale with zero resources},
  booktitle    = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
                  Communication Association, Makuhari, Chiba, Japan, September 26-30,
                  2010},
  pages        = {1676--1679},
  publisher    = {{ISCA}},
  year         = {2010},
  url          = {https://doi.org/10.21437/Interspeech.2010-483},
  doi          = {10.21437/INTERSPEECH.2010-483},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/JansenCH10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/JansenN09,
  author       = {Aren Jansen and
                  Partha Niyogi},
  title        = {Point process models for event-based speech recognition},
  journal      = {Speech Commun.},
  volume       = {51},
  number       = {12},
  pages        = {1155--1168},
  year         = {2009},
  url          = {https://doi.org/10.1016/j.specom.2009.05.008},
  doi          = {10.1016/J.SPECOM.2009.05.008},
  timestamp    = {Sat, 22 Feb 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/speech/JansenN09.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/JansenN09,
  author       = {Aren Jansen and
                  Partha Niyogi},
  title        = {Point Process Models for Spotting Keywords in Continuous Speech},
  journal      = {{IEEE} Trans. Speech Audio Process.},
  volume       = {17},
  number       = {8},
  pages        = {1457--1470},
  year         = {2009},
  url          = {https://doi.org/10.1109/TASL.2009.2021307},
  doi          = {10.1109/TASL.2009.2021307},
  timestamp    = {Sun, 17 May 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/taslp/JansenN09.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/JansenN09,
  author       = {Aren Jansen and
                  Partha Niyogi},
  title        = {Robust keyword spotting with rapidly adapting point process models},
  booktitle    = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech
                  Communication Association, Brighton, United Kingdom, September 6-10,
                  2009},
  pages        = {2767--2770},
  publisher    = {{ISCA}},
  year         = {2009},
  url          = {https://doi.org/10.21437/Interspeech.2009-707},
  doi          = {10.21437/INTERSPEECH.2009-707},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/JansenN09.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/JansenN08,
  author       = {Aren Jansen and
                  Partha Niyogi},
  title        = {A hierarchical point process model for speech recognition},
  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        = {4093--4096},
  publisher    = {{IEEE}},
  year         = {2008},
  url          = {https://doi.org/10.1109/ICASSP.2008.4518554},
  doi          = {10.1109/ICASSP.2008.4518554},
  timestamp    = {Fri, 19 May 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/JansenN08.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/JansenN07,
  author       = {Aren Jansen and
                  Partha Niyogi},
  title        = {Semi-supervised learning of speech sounds},
  booktitle    = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech
                  Communication Association, Antwerp, Belgium, August 27-31, 2007},
  pages        = {86--89},
  publisher    = {{ISCA}},
  year         = {2007},
  url          = {https://doi.org/10.21437/Interspeech.2007-35},
  doi          = {10.21437/INTERSPEECH.2007-35},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/JansenN07.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/JansenN06,
  author       = {Aren Jansen and
                  Partha Niyogi},
  title        = {Intrinsic Fourier Analysis on the Manifold of Speech Sounds},
  booktitle    = {2006 {IEEE} International Conference on Acoustics Speech and Signal
                  Processing, {ICASSP} 2006, Toulouse, France, May 14-19, 2006},
  pages        = {241--244},
  publisher    = {{IEEE}},
  year         = {2006},
  url          = {https://doi.org/10.1109/ICASSP.2006.1660002},
  doi          = {10.1109/ICASSP.2006.1660002},
  timestamp    = {Mon, 22 Jun 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/JansenN06.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
a service of  Schloss Dagstuhl - Leibniz Center for Informatics