Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Wei-Ning Hsu
@article{DBLP:journals/corr/abs-2403-14402,
author = {HyoJung Han and
Mohamed Anwar and
Juan Pino and
Wei{-}Ning Hsu and
Marine Carpuat and
Bowen Shi and
Changhan Wang},
title = {{XLAVS-R:} Cross-Lingual Audio-Visual Speech Representation Learning
for Noise-Robust Speech Perception},
journal = {CoRR},
volume = {abs/2403.14402},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2403.14402},
doi = {10.48550/ARXIV.2403.14402},
eprinttype = {arXiv},
eprint = {2403.14402},
timestamp = {Tue, 09 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2403-14402.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/ChenTYDKCTDSGIP23,
author = {Peng{-}Jen Chen and
Kevin Tran and
Yilin Yang and
Jingfei Du and
Justine Kao and
Yu{-}An Chung and
Paden Tomasello and
Paul{-}Ambroise Duquenne and
Holger Schwenk and
Hongyu Gong and
Hirofumi Inaguma and
Sravya Popuri and
Changhan Wang and
Juan Pino and
Wei{-}Ning Hsu and
Ann Lee},
editor = {Anna Rogers and
Jordan L. Boyd{-}Graber and
Naoaki Okazaki},
title = {Speech-to-Speech Translation for a Real-world Unwritten Language},
booktitle = {Findings of the Association for Computational Linguistics: {ACL} 2023,
Toronto, Canada, July 9-14, 2023},
pages = {4969--4983},
publisher = {Association for Computational Linguistics},
year = {2023},
url = {https://doi.org/10.18653/v1/2023.findings-acl.307},
doi = {10.18653/V1/2023.FINDINGS-ACL.307},
timestamp = {Thu, 10 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/acl/ChenTYDKCTDSGIP23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/WangICK0HA023,
author = {Changhan Wang and
Hirofumi Inaguma and
Peng{-}Jen Chen and
Ilia Kulikov and
Yun Tang and
Wei{-}Ning Hsu and
Michael Auli and
Juan Pino},
editor = {Anna Rogers and
Jordan L. Boyd{-}Graber and
Naoaki Okazaki},
title = {Simple and Effective Unsupervised Speech Translation},
booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational
Linguistics (Volume 1: Long Papers), {ACL} 2023, Toronto, Canada,
July 9-14, 2023},
pages = {10771--10784},
publisher = {Association for Computational Linguistics},
year = {2023},
url = {https://doi.org/10.18653/v1/2023.acl-long.602},
doi = {10.18653/V1/2023.ACL-LONG.602},
timestamp = {Thu, 10 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/acl/WangICK0HA023.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/LianBHA23,
author = {Jiachen Lian and
Alexei Baevski and
Wei{-}Ning Hsu and
Michael Auli},
title = {Av-Data2Vec: Self-Supervised Learning of Audio-Visual Speech Representations
with Contextualized Target Representations},
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/ASRU57964.2023.10389642},
doi = {10.1109/ASRU57964.2023.10389642},
timestamp = {Tue, 13 Feb 2024 21:21:14 +0100},
biburl = {https://dblp.org/rec/conf/asru/LianBHA23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/HsuRSDA23,
author = {Wei{-}Ning Hsu and
Tal Remez and
Bowen Shi and
Jacob Donley and
Yossi Adi},
title = {ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal
and Generalized Speech Regeneration},
booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2023, Vancouver, BC, Canada, June 17-24, 2023},
pages = {18796--18806},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/CVPR52729.2023.01802},
doi = {10.1109/CVPR52729.2023.01802},
timestamp = {Tue, 29 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/HsuRSDA23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/ChouCHLBCBA23,
author = {Ju{-}Chieh Chou and
Chung{-}Ming Chien and
Wei{-}Ning Hsu and
Karen Livescu and
Arun Babu and
Alexis Conneau and
Alexei Baevski and
Michael Auli},
editor = {Houda Bouamor and
Juan Pino and
Kalika Bali},
title = {Toward Joint Language Modeling for Speech Units and Text},
booktitle = {Findings of the Association for Computational Linguistics: {EMNLP}
2023, Singapore, December 6-10, 2023},
pages = {6582--6593},
publisher = {Association for Computational Linguistics},
year = {2023},
url = {https://doi.org/10.18653/v1/2023.findings-emnlp.438},
doi = {10.18653/V1/2023.FINDINGS-EMNLP.438},
timestamp = {Fri, 12 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/emnlp/ChouCHLBCBA23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/DiwanYHTCHM23,
author = {Anuj Diwan and
Ching{-}Feng Yeh and
Wei{-}Ning Hsu and
Paden Tomasello and
Eunsol Choi and
David Harwath and
Abdelrahman Mohamed},
title = {Continual Learning for On-Device Speech Recognition Using Disentangled
Conformers},
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/ICASSP49357.2023.10095484},
doi = {10.1109/ICASSP49357.2023.10095484},
timestamp = {Sun, 05 Nov 2023 16:51:21 +0100},
biburl = {https://dblp.org/rec/conf/icassp/DiwanYHTCHM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ElkahkyHTNAACDM23,
author = {Ali Elkahky and
Wei{-}Ning Hsu and
Paden Tomasello and
Tu Anh Nguyen and
Robin Algayres and
Yossi Adi and
Jade Copet and
Emmanuel Dupoux and
Abdelrahman Mohamed},
title = {Do Coarser Units Benefit Cluster Prediction-Based Speech Pre-Training?},
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/ICASSP49357.2023.10096788},
doi = {10.1109/ICASSP49357.2023.10096788},
timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/ElkahkyHTNAACDM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/FazelZarandiH23,
author = {Maryam Fazel{-}Zarandi and
Wei{-}Ning Hsu},
title = {Cocktail Hubert: Generalized Self-Supervised Pre-Training for Mixture
and Single-Source 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/ICASSP49357.2023.10096630},
doi = {10.1109/ICASSP49357.2023.10096630},
timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/FazelZarandiH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SanabriaHBA23,
author = {Ramon Sanabria and
Wei{-}Ning Hsu and
Alexei Baevski and
Michael Auli},
title = {Measuring the Impact of Domain Factors in Self-Supervised Pre-Training},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} 2023 - Workshops, Rhodes Island, Greece, June 4-10, 2023},
pages = {1--5},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ICASSPW59220.2023.10193184},
doi = {10.1109/ICASSPW59220.2023.10193184},
timestamp = {Mon, 07 Aug 2023 15:56:26 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SanabriaHBA23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AghajanyanYCHHZ23,
author = {Armen Aghajanyan and
Lili Yu and
Alexis Conneau and
Wei{-}Ning Hsu and
Karen Hambardzumyan and
Susan Zhang and
Stephen Roller and
Naman Goyal and
Omer Levy and
Luke Zettlemoyer},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Scaling Laws for Generative Mixed-Modal Language Models},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {265--279},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/aghajanyan23a.html},
timestamp = {Mon, 28 Aug 2023 17:23:08 +0200},
biburl = {https://dblp.org/rec/conf/icml/AghajanyanYCHHZ23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/BaevskiBHA23,
author = {Alexei Baevski and
Arun Babu and
Wei{-}Ning Hsu and
Michael Auli},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Efficient Self-supervised Learning with Contextualized Target Representations
for Vision, Speech and Language},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {1416--1429},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/baevski23a.html},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/BaevskiBHA23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LeVSKSMWMAMH23,
author = {Matthew Le and
Apoorv Vyas and
Bowen Shi and
Brian Karrer and
Leda Sari and
Rashel Moritz and
Mary Williamson and
Vimal Manohar and
Yossi Adi and
Jay Mahadeokar and
Wei{-}Ning Hsu},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Voicebox: Text-Guided Multilingual Universal Speech Generation at
Scale},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/2d8911db9ecedf866015091b28946e15-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/LeVSKSMWMAMH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LiuCAHG23,
author = {Alexander H. Liu and
Heng{-}Jui Chang and
Michael Auli and
Wei{-}Ning Hsu and
Jim Glass},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {DinoSR: Self-Distillation and Online Clustering for Self-supervised
Speech Representation Learning},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/b6404bf461c3c3186bdf5f55756af908-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/LiuCAHG23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-00652,
author = {Ching{-}Feng Yeh and
Wei{-}Ning Hsu and
Paden Tomasello and
Abdelrahman Mohamed},
title = {Efficient Speech Representation Learning with Low-Bit Quantization},
journal = {CoRR},
volume = {abs/2301.00652},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.00652},
doi = {10.48550/ARXIV.2301.00652},
eprinttype = {arXiv},
eprint = {2301.00652},
timestamp = {Tue, 10 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-00652.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-03728,
author = {Armen Aghajanyan and
Lili Yu and
Alexis Conneau and
Wei{-}Ning Hsu and
Karen Hambardzumyan and
Susan Zhang and
Stephen Roller and
Naman Goyal and
Omer Levy and
Luke Zettlemoyer},
title = {Scaling Laws for Generative Mixed-Modal Language Models},
journal = {CoRR},
volume = {abs/2301.03728},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.03728},
doi = {10.48550/ARXIV.2301.03728},
eprinttype = {arXiv},
eprint = {2301.03728},
timestamp = {Thu, 19 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-03728.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-06419,
author = {Jiachen Lian and
Alexei Baevski and
Wei{-}Ning Hsu and
Michael Auli},
title = {AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations
with Contextualized Target Representations},
journal = {CoRR},
volume = {abs/2302.06419},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.06419},
doi = {10.48550/ARXIV.2302.06419},
eprinttype = {arXiv},
eprint = {2302.06419},
timestamp = {Mon, 20 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-06419.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-00628,
author = {Mohamed Anwar and
Bowen Shi and
Vedanuj Goswami and
Wei{-}Ning Hsu and
Juan Pino and
Changhan Wang},
title = {MuAViC: {A} Multilingual Audio-Visual Corpus for Robust Speech Recognition
and Robust Speech-to-Text Translation},
journal = {CoRR},
volume = {abs/2303.00628},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2303.00628},
doi = {10.48550/ARXIV.2303.00628},
eprinttype = {arXiv},
eprint = {2303.00628},
timestamp = {Wed, 19 Apr 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2303-00628.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-11131,
author = {Maryam Fazel{-}Zarandi and
Wei{-}Ning Hsu},
title = {Cocktail HuBERT: Generalized Self-Supervised Pre-training for Mixture
and Single-Source Speech},
journal = {CoRR},
volume = {abs/2303.11131},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2303.11131},
doi = {10.48550/ARXIV.2303.11131},
eprinttype = {arXiv},
eprint = {2303.11131},
timestamp = {Wed, 22 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2303-11131.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-10005,
author = {Alexander H. Liu and
Heng{-}Jui Chang and
Michael Auli and
Wei{-}Ning Hsu and
James R. Glass},
title = {DinoSR: Self-Distillation and Online Clustering for Self-supervised
Speech Representation Learning},
journal = {CoRR},
volume = {abs/2305.10005},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.10005},
doi = {10.48550/ARXIV.2305.10005},
eprinttype = {arXiv},
eprint = {2305.10005},
timestamp = {Wed, 24 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-10005.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-13516,
author = {Vineel Pratap and
Andros Tjandra and
Bowen Shi and
Paden Tomasello and
Arun Babu and
Sayani Kundu and
Ali Elkahky and
Zhaoheng Ni and
Apoorv Vyas and
Maryam Fazel{-}Zarandi and
Alexei Baevski and
Yossi Adi and
Xiaohui Zhang and
Wei{-}Ning Hsu and
Alexis Conneau and
Michael Auli},
title = {Scaling Speech Technology to 1, 000+ Languages},
journal = {CoRR},
volume = {abs/2305.13516},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.13516},
doi = {10.48550/ARXIV.2305.13516},
eprinttype = {arXiv},
eprint = {2305.13516},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-13516.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-15687,
author = {Matthew Le and
Apoorv Vyas and
Bowen Shi and
Brian Karrer and
Leda Sari and
Rashel Moritz and
Mary Williamson and
Vimal Manohar and
Yossi Adi and
Jay Mahadeokar and
Wei{-}Ning Hsu},
title = {Voicebox: Text-Guided Multilingual Universal Speech Generation at
Scale},
journal = {CoRR},
volume = {abs/2306.15687},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.15687},
doi = {10.48550/ARXIV.2306.15687},
eprinttype = {arXiv},
eprint = {2306.15687},
timestamp = {Mon, 03 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-15687.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2308-05725,
author = {Tu Anh Nguyen and
Wei{-}Ning Hsu and
Antony D'Avirro and
Bowen Shi and
Itai Gat and
Maryam Fazel{-}Zarandi and
Tal Remez and
Jade Copet and
Gabriel Synnaeve and
Michael Hassid and
Felix Kreuk and
Yossi Adi and
Emmanuel Dupoux},
title = {{EXPRESSO:} {A} Benchmark and Analysis of Discrete Expressive Speech
Resynthesis},
journal = {CoRR},
volume = {abs/2308.05725},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2308.05725},
doi = {10.48550/ARXIV.2308.05725},
eprinttype = {arXiv},
eprint = {2308.05725},
timestamp = {Wed, 23 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2308-05725.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-17020,
author = {Po{-}Chun Hsu and
Ali Elkahky and
Wei{-}Ning Hsu and
Yossi Adi and
Tu Anh Nguyen and
Jade Copet and
Emmanuel Dupoux and
Hung{-}yi Lee and
Abdelrahman Mohamed},
title = {Low-Resource Self-Supervised Learning with SSL-Enhanced {TTS}},
journal = {CoRR},
volume = {abs/2309.17020},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.17020},
doi = {10.48550/ARXIV.2309.17020},
eprinttype = {arXiv},
eprint = {2309.17020},
timestamp = {Tue, 17 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-17020.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-08715,
author = {Ju{-}Chieh Chou and
Chung{-}Ming Chien and
Wei{-}Ning Hsu and
Karen Livescu and
Arun Babu and
Alexis Conneau and
Alexei Baevski and
Michael Auli},
title = {Toward Joint Language Modeling for Speech Units and Text},
journal = {CoRR},
volume = {abs/2310.08715},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.08715},
doi = {10.48550/ARXIV.2310.08715},
eprinttype = {arXiv},
eprint = {2310.08715},
timestamp = {Wed, 25 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-08715.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-16338,
author = {Alexander H. Liu and
Matt Le and
Apoorv Vyas and
Bowen Shi and
Andros Tjandra and
Wei{-}Ning Hsu},
title = {Generative Pre-training for Speech with Flow Matching},
journal = {CoRR},
volume = {abs/2310.16338},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.16338},
doi = {10.48550/ARXIV.2310.16338},
eprinttype = {arXiv},
eprint = {2310.16338},
timestamp = {Tue, 31 Oct 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-16338.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2311-02772,
author = {Sungho Jeon and
Ching{-}Feng Yeh and
Hakan Inan and
Wei{-}Ning Hsu and
Rashi Rungta and
Yashar Mehdad and
Daniel Bikel},
title = {Attention or Convolution: Transformer Encoders in Audio Language Models
for Inference Efficiency},
journal = {CoRR},
volume = {abs/2311.02772},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2311.02772},
doi = {10.48550/ARXIV.2311.02772},
eprinttype = {arXiv},
eprint = {2311.02772},
timestamp = {Wed, 08 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2311-02772.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-15821,
author = {Apoorv Vyas and
Bowen Shi and
Matthew Le and
Andros Tjandra and
Yi{-}Chiao Wu and
Baishan Guo and
Jiemin Zhang and
Xinyue Zhang and
Robert Adkins and
William Ngan and
Jeff Wang and
Ivan Cruz and
Bapi Akula and
Akinniyi Akinyemi and
Brian Ellis and
Rashel Moritz and
Yael Yungster and
Alice Rakotoarison and
Liang Tan and
Chris Summers and
Carleigh Wood and
Joshua Lane and
Mary Williamson and
Wei{-}Ning Hsu},
title = {Audiobox: Unified Audio Generation with Natural Language Prompts},
journal = {CoRR},
volume = {abs/2312.15821},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.15821},
doi = {10.48550/ARXIV.2312.15821},
eprinttype = {arXiv},
eprint = {2312.15821},
timestamp = {Tue, 16 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-15821.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/TangGDWHGBLMAP22,
author = {Yun Tang and
Hongyu Gong and
Ning Dong and
Changhan Wang and
Wei{-}Ning Hsu and
Jiatao Gu and
Alexei Baevski and
Xian Li and
Abdelrahman Mohamed and
Michael Auli and
Juan Miguel Pino},
editor = {Smaranda Muresan and
Preslav Nakov and
Aline Villavicencio},
title = {Unified Speech-Text Pre-training for Speech Translation and Recognition},
booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational
Linguistics (Volume 1: Long Papers), {ACL} 2022, Dublin, Ireland,
May 22-27, 2022},
pages = {1488--1499},
publisher = {Association for Computational Linguistics},
year = {2022},
url = {https://doi.org/10.18653/v1/2022.acl-long.105},
doi = {10.18653/V1/2022.ACL-LONG.105},
timestamp = {Tue, 27 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/acl/TangGDWHGBLMAP22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/LeeCWGPMPAHTPH22,
author = {Ann Lee and
Peng{-}Jen Chen and
Changhan Wang and
Jiatao Gu and
Sravya Popuri and
Xutai Ma and
Adam Polyak and
Yossi Adi and
Qing He and
Yun Tang and
Juan Pino and
Wei{-}Ning Hsu},
editor = {Smaranda Muresan and
Preslav Nakov and
Aline Villavicencio},
title = {Direct Speech-to-Speech Translation With Discrete Units},
booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational
Linguistics (Volume 1: Long Papers), {ACL} 2022, Dublin, Ireland,
May 22-27, 2022},
pages = {3327--3339},
publisher = {Association for Computational Linguistics},
year = {2022},
url = {https://doi.org/10.18653/v1/2022.acl-long.235},
doi = {10.18653/V1/2022.ACL-LONG.235},
timestamp = {Tue, 27 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/acl/LeeCWGPMPAHTPH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/KharitonovLPACL22,
author = {Eugene Kharitonov and
Ann Lee and
Adam Polyak and
Yossi Adi and
Jade Copet and
Kushal Lakhotia and
Tu Anh Nguyen and
Morgane Rivi{\`{e}}re and
Abdelrahman Mohamed and
Emmanuel Dupoux and
Wei{-}Ning Hsu},
editor = {Smaranda Muresan and
Preslav Nakov and
Aline Villavicencio},
title = {Text-Free Prosody-Aware Generative Spoken Language Modeling},
booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational
Linguistics (Volume 1: Long Papers), {ACL} 2022, Dublin, Ireland,
May 22-27, 2022},
pages = {8666--8681},
publisher = {Association for Computational Linguistics},
year = {2022},
url = {https://doi.org/10.18653/v1/2022.acl-long.593},
doi = {10.18653/V1/2022.ACL-LONG.593},
timestamp = {Thu, 06 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/acl/KharitonovLPACL22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/KreukPCKNRHMDA22,
author = {Felix Kreuk and
Adam Polyak and
Jade Copet and
Eugene Kharitonov and
Tu Anh Nguyen and
Morgane Rivi{\`{e}}re and
Wei{-}Ning Hsu and
Abdelrahman Mohamed and
Emmanuel Dupoux and
Yossi Adi},
editor = {Yoav Goldberg and
Zornitsa Kozareva and
Yue Zhang},
title = {Textless Speech Emotion Conversion using Discrete {\&} Decomposed
Representations},
booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural
Language Processing, {EMNLP} 2022, Abu Dhabi, United Arab Emirates,
December 7-11, 2022},
pages = {11200--11214},
publisher = {Association for Computational Linguistics},
year = {2022},
url = {https://doi.org/10.18653/v1/2022.emnlp-main.769},
doi = {10.18653/V1/2022.EMNLP-MAIN.769},
timestamp = {Thu, 10 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/emnlp/KreukPCKNRHMDA22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/ShiHLM22,
author = {Bowen Shi and
Wei{-}Ning Hsu and
Kushal Lakhotia and
Abdelrahman Mohamed},
title = {Learning Audio-Visual Speech Representation by Masked Multimodal Cluster
Prediction},
booktitle = {The Tenth International Conference on Learning Representations, {ICLR}
2022, Virtual Event, April 25-29, 2022},
publisher = {OpenReview.net},
year = {2022},
url = {https://openreview.net/forum?id=Z1Qlm11uOM},
timestamp = {Sat, 20 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/ShiHLM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/BaevskiHXBGA22,
author = {Alexei Baevski and
Wei{-}Ning Hsu and
Qiantong Xu and
Arun Babu and
Jiatao Gu and
Michael Auli},
editor = {Kamalika Chaudhuri and
Stefanie Jegelka and
Le Song and
Csaba Szepesv{\'{a}}ri and
Gang Niu and
Sivan Sabato},
title = {data2vec: {A} General Framework for Self-supervised Learning in Speech,
Vision and Language},
booktitle = {International Conference on Machine Learning, {ICML} 2022, 17-23 July
2022, Baltimore, Maryland, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {162},
pages = {1298--1312},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v162/baevski22a.html},
timestamp = {Tue, 12 Jul 2022 17:36:52 +0200},
biburl = {https://dblp.org/rec/conf/icml/BaevskiHXBGA22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiuLHABG22,
author = {Alexander H. Liu and
Cheng{-}I Lai and
Wei{-}Ning Hsu and
Michael Auli and
Alexei Baevski and
James R. Glass},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Simple and Effective Unsupervised Speech Synthesis},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {843--847},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-11071},
doi = {10.21437/INTERSPEECH.2022-11071},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiuLHABG22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ShiHM22,
author = {Bowen Shi and
Wei{-}Ning Hsu and
Abdelrahman Mohamed},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Robust Self-Supervised Audio-Visual Speech Recognition},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {2118--2122},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-99},
doi = {10.21437/INTERSPEECH.2022-99},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ShiHM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/VyasHAB22,
author = {Apoorv Vyas and
Wei{-}Ning Hsu and
Michael Auli and
Alexei Baevski},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {On-demand compute reduction with stochastic wav2vec 2.0},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {3048--3052},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-10584},
doi = {10.21437/INTERSPEECH.2022-10584},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/VyasHAB22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ShiMH22,
author = {Bowen Shi and
Abdelrahman Mohamed and
Wei{-}Ning Hsu},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {4785--4789},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-885},
doi = {10.21437/INTERSPEECH.2022-885},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ShiMH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PopuriCWPAGHL22,
author = {Sravya Popuri and
Peng{-}Jen Chen and
Changhan Wang and
Juan Pino and
Yossi Adi and
Jiatao Gu and
Wei{-}Ning Hsu and
Ann Lee},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Enhanced Direct Speech-to-Speech Translation Using Self-supervised
Pre-training and Data Augmentation},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {5195--5199},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-11032},
doi = {10.21437/INTERSPEECH.2022-11032},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PopuriCWPAGHL22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/naacl/LeeGDSCWPAPGH22,
author = {Ann Lee and
Hongyu Gong and
Paul{-}Ambroise Duquenne and
Holger Schwenk and
Peng{-}Jen Chen and
Changhan Wang and
Sravya Popuri and
Yossi Adi and
Juan Miguel Pino and
Jiatao Gu and
Wei{-}Ning Hsu},
editor = {Marine Carpuat and
Marie{-}Catherine de Marneffe and
Iv{\'{a}}n Vladimir Meza Ru{\'{\i}}z},
title = {Textless Speech-to-Speech Translation on Real Data},
booktitle = {Proceedings of the 2022 Conference of the North American Chapter of
the Association for Computational Linguistics: Human Language Technologies,
{NAACL} 2022, Seattle, WA, United States, July 10-15, 2022},
pages = {860--872},
publisher = {Association for Computational Linguistics},
year = {2022},
url = {https://doi.org/10.18653/v1/2022.naacl-main.63},
doi = {10.18653/V1/2022.NAACL-MAIN.63},
timestamp = {Tue, 31 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/naacl/LeeGDSCWPAPGH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/HsuS22,
author = {Wei{-}Ning Hsu and
Bowen Shi},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer
to Unlabeled Modality},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/853e781cb2af58956ed5c89aa59da3fc-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/HsuS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/LiuHAB22,
author = {Alexander H. Liu and
Wei{-}Ning Hsu and
Michael Auli and
Alexei Baevski},
title = {Towards End-to-End Unsupervised Speech Recognition},
booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2022, Doha, Qatar,
January 9-12, 2023},
pages = {221--228},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/SLT54892.2023.10023187},
doi = {10.1109/SLT54892.2023.10023187},
timestamp = {Mon, 06 Feb 2023 22:19:30 +0100},
biburl = {https://dblp.org/rec/conf/slt/LiuHAB22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/TomaselloSLHLSECHAANDZM22,
author = {Paden Tomasello and
Akshat Shrivastava and
Daniel Lazar and
Po{-}Chun Hsu and
Duc Le and
Adithya Sagar and
Ali Elkahky and
Jade Copet and
Wei{-}Ning Hsu and
Yossi Adi and
Robin Algayres and
Tu Anh Nguyen and
Emmanuel Dupoux and
Luke Zettlemoyer and
Abdelrahman Mohamed},
title = {Stop: {A} Dataset for Spoken Task Oriented Semantic Parsing},
booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2022, Doha, Qatar,
January 9-12, 2023},
pages = {991--998},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/SLT54892.2023.10022703},
doi = {10.1109/SLT54892.2023.10022703},
timestamp = {Mon, 11 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/slt/TomaselloSLHLSECHAANDZM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-01763,
author = {Bowen Shi and
Wei{-}Ning Hsu and
Abdelrahman Mohamed},
title = {Robust Self-Supervised Audio-Visual Speech Recognition},
journal = {CoRR},
volume = {abs/2201.01763},
year = {2022},
url = {https://arxiv.org/abs/2201.01763},
eprinttype = {arXiv},
eprint = {2201.01763},
timestamp = {Mon, 10 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-01763.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-02184,
author = {Bowen Shi and
Wei{-}Ning Hsu and
Kushal Lakhotia and
Abdelrahman Mohamed},
title = {Learning Audio-Visual Speech Representation by Masked Multimodal Cluster
Prediction},
journal = {CoRR},
volume = {abs/2201.02184},
year = {2022},
url = {https://arxiv.org/abs/2201.02184},
eprinttype = {arXiv},
eprint = {2201.02184},
timestamp = {Mon, 10 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-02184.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-03555,
author = {Alexei Baevski and
Wei{-}Ning Hsu and
Qiantong Xu and
Arun Babu and
Jiatao Gu and
Michael Auli},
title = {data2vec: {A} General Framework for Self-supervised Learning in Speech,
Vision and Language},
journal = {CoRR},
volume = {abs/2202.03555},
year = {2022},
url = {https://arxiv.org/abs/2202.03555},
eprinttype = {arXiv},
eprint = {2202.03555},
timestamp = {Wed, 09 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-03555.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-07359,
author = {Eugene Kharitonov and
Jade Copet and
Kushal Lakhotia and
Tu Anh Nguyen and
Paden Tomasello and
Ann Lee and
Ali Elkahky and
Wei{-}Ning Hsu and
Abdelrahman Mohamed and
Emmanuel Dupoux and
Yossi Adi},
title = {textless-lib: a Library for Textless Spoken Language Processing},
journal = {CoRR},
volume = {abs/2202.07359},
year = {2022},
url = {https://arxiv.org/abs/2202.07359},
eprinttype = {arXiv},
eprint = {2202.07359},
timestamp = {Mon, 14 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-07359.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-00648,
author = {Ramon Sanabria and
Wei{-}Ning Hsu and
Alexei Baevski and
Michael Auli},
title = {Measuring the Impact of Individual Domain Factors in Self-Supervised
Pre-Training},
journal = {CoRR},
volume = {abs/2203.00648},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.00648},
doi = {10.48550/ARXIV.2203.00648},
eprinttype = {arXiv},
eprint = {2203.00648},
timestamp = {Wed, 16 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-00648.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-16502,
author = {Tu Anh Nguyen and
Eugene Kharitonov and
Jade Copet and
Yossi Adi and
Wei{-}Ning Hsu and
Ali Elkahky and
Paden Tomasello and
Robin Algayres and
Beno{\^{\i}}t Sagot and
Abdelrahman Mohamed and
Emmanuel Dupoux},
title = {Generative Spoken Dialogue Language Modeling},
journal = {CoRR},
volume = {abs/2203.16502},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.16502},
doi = {10.48550/ARXIV.2203.16502},
eprinttype = {arXiv},
eprint = {2203.16502},
timestamp = {Mon, 04 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-16502.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-02492,
author = {Alexander H. Liu and
Wei{-}Ning Hsu and
Michael Auli and
Alexei Baevski},
title = {Towards End-to-end Unsupervised Speech Recognition},
journal = {CoRR},
volume = {abs/2204.02492},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.02492},
doi = {10.48550/ARXIV.2204.02492},
eprinttype = {arXiv},
eprint = {2204.02492},
timestamp = {Tue, 12 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-02492.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-02524,
author = {Alexander H. Liu and
Cheng{-}I Jeff Lai and
Wei{-}Ning Hsu and
Michael Auli and
Alexei Baevski and
James R. Glass},
title = {Simple and Effective Unsupervised Speech Synthesis},
journal = {CoRR},
volume = {abs/2204.02524},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.02524},
doi = {10.48550/ARXIV.2204.02524},
eprinttype = {arXiv},
eprint = {2204.02524},
timestamp = {Mon, 25 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-02524.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-02967,
author = {Sravya Popuri and
Peng{-}Jen Chen and
Changhan Wang and
Juan Pino and
Yossi Adi and
Jiatao Gu and
Wei{-}Ning Hsu and
Ann Lee},
title = {Enhanced Direct Speech-to-Speech Translation Using Self-supervised
Pre-training and Data Augmentation},
journal = {CoRR},
volume = {abs/2204.02967},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.02967},
doi = {10.48550/ARXIV.2204.02967},
eprinttype = {arXiv},
eprint = {2204.02967},
timestamp = {Wed, 19 Apr 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-02967.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-05409,
author = {Yun Tang and
Hongyu Gong and
Ning Dong and
Changhan Wang and
Wei{-}Ning Hsu and
Jiatao Gu and
Alexei Baevski and
Xian Li and
Abdelrahman Mohamed and
Michael Auli and
Juan Miguel Pino},
title = {Unified Speech-Text Pre-training for Speech Translation and Recognition},
journal = {CoRR},
volume = {abs/2204.05409},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.05409},
doi = {10.48550/ARXIV.2204.05409},
eprinttype = {arXiv},
eprint = {2204.05409},
timestamp = {Tue, 27 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-05409.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-11934,
author = {Apoorv Vyas and
Wei{-}Ning Hsu and
Michael Auli and
Alexei Baevski},
title = {On-demand compute reduction with stochastic wav2vec 2.0},
journal = {CoRR},
volume = {abs/2204.11934},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.11934},
doi = {10.48550/ARXIV.2204.11934},
eprinttype = {arXiv},
eprint = {2204.11934},
timestamp = {Thu, 28 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-11934.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-07180,
author = {Bowen Shi and
Abdelrahman Mohamed and
Wei{-}Ning Hsu},
title = {Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT},
journal = {CoRR},
volume = {abs/2205.07180},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.07180},
doi = {10.48550/ARXIV.2205.07180},
eprinttype = {arXiv},
eprint = {2205.07180},
timestamp = {Wed, 18 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-07180.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-07036,
author = {Wei{-}Ning Hsu and
Bowen Shi},
title = {A Single Self-Supervised Model for Many Speech Modalities Enables
Zero-Shot Modality Transfer},
journal = {CoRR},
volume = {abs/2207.07036},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2207.07036},
doi = {10.48550/ARXIV.2207.07036},
eprinttype = {arXiv},
eprint = {2207.07036},
timestamp = {Tue, 19 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2207-07036.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-10643,
author = {Paden Tomasello and
Akshat Shrivastava and
Daniel Lazar and
Po{-}Chun Hsu and
Duc Le and
Adithya Sagar and
Ali Elkahky and
Jade Copet and
Wei{-}Ning Hsu and
Yossef Mordechay and
Robin Algayres and
Tu Anh Nguyen and
Emmanuel Dupoux and
Luke Zettlemoyer and
Abdelrahman Mohamed},
title = {{STOP:} {A} dataset for Spoken Task Oriented Semantic Parsing},
journal = {CoRR},
volume = {abs/2207.10643},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2207.10643},
doi = {10.48550/ARXIV.2207.10643},
eprinttype = {arXiv},
eprint = {2207.10643},
timestamp = {Mon, 25 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2207-10643.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-10191,
author = {Changhan Wang and
Hirofumi Inaguma and
Peng{-}Jen Chen and
Ilia Kulikov and
Yun Tang and
Wei{-}Ning Hsu and
Michael Auli and
Juan Pino},
title = {Simple and Effective Unsupervised Speech Translation},
journal = {CoRR},
volume = {abs/2210.10191},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.10191},
doi = {10.48550/ARXIV.2210.10191},
eprinttype = {arXiv},
eprint = {2210.10191},
timestamp = {Tue, 27 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-10191.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-06474,
author = {Peng{-}Jen Chen and
Kevin Tran and
Yilin Yang and
Jingfei Du and
Justine Kao and
Yu{-}An Chung and
Paden Tomasello and
Paul{-}Ambroise Duquenne and
Holger Schwenk and
Hongyu Gong and
Hirofumi Inaguma and
Sravya Popuri and
Changhan Wang and
Juan Miguel Pino and
Wei{-}Ning Hsu and
Ann Lee},
title = {Speech-to-Speech Translation For {A} Real-world Unwritten Language},
journal = {CoRR},
volume = {abs/2211.06474},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.06474},
doi = {10.48550/ARXIV.2211.06474},
eprinttype = {arXiv},
eprint = {2211.06474},
timestamp = {Tue, 31 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-06474.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-01393,
author = {Anuj Diwan and
Ching{-}Feng Yeh and
Wei{-}Ning Hsu and
Paden Tomasello and
Eunsol Choi and
David Harwath and
Abdelrahman Mohamed},
title = {Continual Learning for On-Device Speech Recognition using Disentangled
Conformers},
journal = {CoRR},
volume = {abs/2212.01393},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.01393},
doi = {10.48550/ARXIV.2212.01393},
eprinttype = {arXiv},
eprint = {2212.01393},
timestamp = {Thu, 08 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-01393.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-07525,
author = {Alexei Baevski and
Arun Babu and
Wei{-}Ning Hsu and
Michael Auli},
title = {Efficient Self-supervised Learning with Contextualized Target Representations
for Vision, Speech and Language},
journal = {CoRR},
volume = {abs/2212.07525},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.07525},
doi = {10.48550/ARXIV.2212.07525},
eprinttype = {arXiv},
eprint = {2212.07525},
timestamp = {Mon, 02 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-07525.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-11377,
author = {Wei{-}Ning Hsu and
Tal Remez and
Bowen Shi and
Jacob Donley and
Yossi Adi},
title = {ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal
and Generalized Speech Enhancement},
journal = {CoRR},
volume = {abs/2212.11377},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.11377},
doi = {10.48550/ARXIV.2212.11377},
eprinttype = {arXiv},
eprint = {2212.11377},
timestamp = {Mon, 02 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-11377.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/HsuBTLSM21,
author = {Wei{-}Ning Hsu and
Benjamin Bolte and
Yao{-}Hung Hubert Tsai and
Kushal Lakhotia and
Ruslan Salakhutdinov and
Abdelrahman Mohamed},
title = {HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction
of Hidden Units},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {29},
pages = {3451--3460},
year = {2021},
url = {https://doi.org/10.1109/TASLP.2021.3122291},
doi = {10.1109/TASLP.2021.3122291},
timestamp = {Wed, 15 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/HsuBTLSM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/HsuHMSG20,
author = {Wei{-}Ning Hsu and
David Harwath and
Tyler Miller and
Christopher Song and
James R. Glass},
editor = {Chengqing Zong and
Fei Xia and
Wenjie Li and
Roberto Navigli},
title = {Text-Free Image-to-Speech Synthesis Using Learned Segmental Units},
booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational
Linguistics and the 11th International Joint Conference on Natural
Language Processing, {ACL/IJCNLP} 2021, (Volume 1: Long Papers), Virtual
Event, August 1-6, 2021},
pages = {5284--5300},
publisher = {Association for Computational Linguistics},
year = {2021},
url = {https://doi.org/10.18653/v1/2021.acl-long.411},
doi = {10.18653/V1/2021.ACL-LONG.411},
timestamp = {Mon, 09 Aug 2021 16:25:37 +0200},
biburl = {https://dblp.org/rec/conf/acl/HsuHMSG20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/ManoharLXHCSZM21,
author = {Vimal Manohar and
Tatiana Likhomanenko and
Qiantong Xu and
Wei{-}Ning Hsu and
Ronan Collobert and
Yatharth Saraf and
Geoffrey Zweig and
Abdelrahman Mohamed},
title = {Kaizen: Continuously Improving Teacher Using Exponential Moving Average
for Semi-Supervised Speech Recognition},
booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
2021, Cartagena, Colombia, December 13-17, 2021},
pages = {518--525},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ASRU51503.2021.9688028},
doi = {10.1109/ASRU51503.2021.9688028},
timestamp = {Wed, 09 Feb 2022 09:03:03 +0100},
biburl = {https://dblp.org/rec/conf/asru/ManoharLXHCSZM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/WangHAPLCGP21,
author = {Changhan Wang and
Wei{-}Ning Hsu and
Yossi Adi and
Adam Polyak and
Ann Lee and
Peng{-}Jen Chen and
Jiatao Gu and
Juan Pino},
editor = {Heike Adel and
Shuming Shi},
title = {fairseq S{\textbackslash}{\^{}}2: {A} Scalable and Integrable Speech
Synthesis Toolkit},
booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural
Language Processing: System Demonstrations, {EMNLP} 2021, Online and
Punta Cana, Dominican Republic, 7-11 November, 2021},
pages = {143--152},
publisher = {Association for Computational Linguistics},
year = {2021},
url = {https://doi.org/10.18653/v1/2021.emnlp-demo.17},
doi = {10.18653/V1/2021.EMNLP-DEMO.17},
timestamp = {Wed, 19 Apr 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/emnlp/WangHAPLCGP21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HsuTBSM21,
author = {Wei{-}Ning Hsu and
Yao{-}Hung Hubert Tsai and
Benjamin Bolte and
Ruslan Salakhutdinov and
Abdelrahman Mohamed},
title = {Hubert: How Much Can a Bad Teacher Benefit {ASR} Pre-Training?},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {6533--6537},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414460},
doi = {10.1109/ICASSP39728.2021.9414460},
timestamp = {Fri, 09 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HsuTBSM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HsuSBLXPK0CSA21,
author = {Wei{-}Ning Hsu and
Anuroop Sriram and
Alexei Baevski and
Tatiana Likhomanenko and
Qiantong Xu and
Vineel Pratap and
Jacob Kahn and
Ann Lee and
Ronan Collobert and
Gabriel Synnaeve and
Michael Auli},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {721--725},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-236},
doi = {10.21437/INTERSPEECH.2021-236},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HsuSBLXPK0CSA21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PolyakACKLHMD21,
author = {Adam Polyak and
Yossi Adi and
Jade Copet and
Eugene Kharitonov and
Kushal Lakhotia and
Wei{-}Ning Hsu and
Abdelrahman Mohamed and
Emmanuel Dupoux},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Speech Resynthesis from Discrete Disentangled Self-Supervised Representations},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {3615--3619},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-475},
doi = {10.21437/INTERSPEECH.2021-475},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PolyakACKLHMD21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BaevskiHCA21,
author = {Alexei Baevski and
Wei{-}Ning Hsu and
Alexis Conneau and
Michael Auli},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Unsupervised Speech Recognition},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {27826--27839},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/ea159dc9788ffac311592613b7f71fbb-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/BaevskiHCA21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/Hsu0SH21,
author = {Wei{-}Ning Hsu and
Ann Lee and
Gabriel Synnaeve and
Awni Y. Hannun},
title = {Semi-Supervised end-to-end Speech Recognition via Local Prior Matching},
booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen,
China, January 19-22, 2021},
pages = {125--132},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/SLT48900.2021.9383552},
doi = {10.1109/SLT48900.2021.9383552},
timestamp = {Tue, 05 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/slt/Hsu0SH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-01192,
author = {Kushal Lakhotia and
Evgeny Kharitonov and
Wei{-}Ning Hsu and
Yossi Adi and
Adam Polyak and
Benjamin Bolte and
Tu Anh Nguyen and
Jade Copet and
Alexei Baevski and
Adelrahman Mohamed and
Emmanuel Dupoux},
title = {Generative Spoken Language Modeling from Raw Audio},
journal = {CoRR},
volume = {abs/2102.01192},
year = {2021},
url = {https://arxiv.org/abs/2102.01192},
eprinttype = {arXiv},
eprint = {2102.01192},
timestamp = {Tue, 09 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-01192.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-00355,
author = {Adam Polyak and
Yossi Adi and
Jade Copet and
Eugene Kharitonov and
Kushal Lakhotia and
Wei{-}Ning Hsu and
Abdelrahman Mohamed and
Emmanuel Dupoux},
title = {Speech Resynthesis from Discrete Disentangled Self-Supervised Representations},
journal = {CoRR},
volume = {abs/2104.00355},
year = {2021},
url = {https://arxiv.org/abs/2104.00355},
eprinttype = {arXiv},
eprint = {2104.00355},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-00355.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-01027,
author = {Wei{-}Ning Hsu and
Anuroop Sriram and
Alexei Baevski and
Tatiana Likhomanenko and
Qiantong Xu and
Vineel Pratap and
Jacob Kahn and
Ann Lee and
Ronan Collobert and
Gabriel Synnaeve and
Michael Auli},
title = {Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training},
journal = {CoRR},
volume = {abs/2104.01027},
year = {2021},
url = {https://arxiv.org/abs/2104.01027},
eprinttype = {arXiv},
eprint = {2104.01027},
timestamp = {Mon, 12 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-01027.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2105-11084,
author = {Alexei Baevski and
Wei{-}Ning Hsu and
Alexis Conneau and
Michael Auli},
title = {Unsupervised Speech Recognition},
journal = {CoRR},
volume = {abs/2105.11084},
year = {2021},
url = {https://arxiv.org/abs/2105.11084},
eprinttype = {arXiv},
eprint = {2105.11084},
timestamp = {Tue, 01 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2105-11084.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-07447,
author = {Wei{-}Ning Hsu and
Benjamin Bolte and
Yao{-}Hung Hubert Tsai and
Kushal Lakhotia and
Ruslan Salakhutdinov and
Abdelrahman Mohamed},
title = {HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction
of Hidden Units},
journal = {CoRR},
volume = {abs/2106.07447},
year = {2021},
url = {https://arxiv.org/abs/2106.07447},
eprinttype = {arXiv},
eprint = {2106.07447},
timestamp = {Wed, 16 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-07447.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-07759,
author = {Vimal Manohar and
Tatiana Likhomanenko and
Qiantong Xu and
Wei{-}Ning Hsu and
Ronan Collobert and
Yatharth Saraf and
Geoffrey Zweig and
Abdelrahman Mohamed},
title = {Kaizen: Continuously improving teacher using Exponential Moving Average
for semi-supervised speech recognition},
journal = {CoRR},
volume = {abs/2106.07759},
year = {2021},
url = {https://arxiv.org/abs/2106.07759},
eprinttype = {arXiv},
eprint = {2106.07759},
timestamp = {Thu, 01 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-07759.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2107-05604,
author = {Ann Lee and
Peng{-}Jen Chen and
Changhan Wang and
Jiatao Gu and
Xutai Ma and
Adam Polyak and
Yossi Adi and
Qing He and
Yun Tang and
Juan Miguel Pino and
Wei{-}Ning Hsu},
title = {Direct speech-to-speech translation with discrete units},
journal = {CoRR},
volume = {abs/2107.05604},
year = {2021},
url = {https://arxiv.org/abs/2107.05604},
eprinttype = {arXiv},
eprint = {2107.05604},
timestamp = {Tue, 27 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-05604.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-03264,
author = {Eugene Kharitonov and
Ann Lee and
Adam Polyak and
Yossi Adi and
Jade Copet and
Kushal Lakhotia and
Tu Anh Nguyen and
Morgane Rivi{\`{e}}re and
Abdelrahman Mohamed and
Emmanuel Dupoux and
Wei{-}Ning Hsu},
title = {Text-Free Prosody-Aware Generative Spoken Language Modeling},
journal = {CoRR},
volume = {abs/2109.03264},
year = {2021},
url = {https://arxiv.org/abs/2109.03264},
eprinttype = {arXiv},
eprint = {2109.03264},
timestamp = {Thu, 06 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-03264.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-06912,
author = {Changhan Wang and
Wei{-}Ning Hsu and
Yossi Adi and
Adam Polyak and
Ann Lee and
Peng{-}Jen Chen and
Jiatao Gu and
Juan Miguel Pino},
title = {fairseq S{\^{}}2: {A} Scalable and Integrable Speech Synthesis Toolkit},
journal = {CoRR},
volume = {abs/2109.06912},
year = {2021},
url = {https://arxiv.org/abs/2109.06912},
eprinttype = {arXiv},
eprint = {2109.06912},
timestamp = {Thu, 06 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-06912.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-08250,
author = {Xutai Ma and
Hongyu Gong and
Danni Liu and
Ann Lee and
Yun Tang and
Peng{-}Jen Chen and
Wei{-}Ning Hsu and
Kenneth Heafield and
Phillip Koehn and
Juan Miguel Pino},
title = {Direct simultaneous speech to speech translation},
journal = {CoRR},
volume = {abs/2110.08250},
year = {2021},
url = {https://arxiv.org/abs/2110.08250},
eprinttype = {arXiv},
eprint = {2110.08250},
timestamp = {Tue, 27 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-08250.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-07402,
author = {Felix Kreuk and
Adam Polyak and
Jade Copet and
Eugene Kharitonov and
Tu Anh Nguyen and
Morgane Rivi{\`{e}}re and
Wei{-}Ning Hsu and
Abdelrahman Mohamed and
Emmanuel Dupoux and
Yossi Adi},
title = {Textless Speech Emotion Conversion using Decomposed and Discrete Representations},
journal = {CoRR},
volume = {abs/2111.07402},
year = {2021},
url = {https://arxiv.org/abs/2111.07402},
eprinttype = {arXiv},
eprint = {2111.07402},
timestamp = {Tue, 16 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-07402.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-08352,
author = {Ann Lee and
Hongyu Gong and
Paul{-}Ambroise Duquenne and
Holger Schwenk and
Peng{-}Jen Chen and
Changhan Wang and
Sravya Popuri and
Juan Miguel Pino and
Jiatao Gu and
Wei{-}Ning Hsu},
title = {Textless Speech-to-Speech Translation on Real Data},
journal = {CoRR},
volume = {abs/2112.08352},
year = {2021},
url = {https://arxiv.org/abs/2112.08352},
eprinttype = {arXiv},
eprint = {2112.08352},
timestamp = {Tue, 31 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-08352.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/HarwathHG20,
author = {David Harwath and
Wei{-}Ning Hsu and
James R. Glass},
title = {Learning Hierarchical Discrete Linguistic Units from Visually-Grounded
Speech},
booktitle = {8th International Conference on Learning Representations, {ICLR} 2020,
Addis Ababa, Ethiopia, April 26-30, 2020},
publisher = {OpenReview.net},
year = {2020},
url = {https://openreview.net/forum?id=B1elCp4KwH},
timestamp = {Thu, 07 May 2020 17:11:47 +0200},
biburl = {https://dblp.org/rec/conf/iclr/HarwathHG20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GumpHG20,
author = {Michael Gump and
Wei{-}Ning Hsu and
James R. Glass},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Unsupervised Methods for Evaluating Speech Representations},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {170--174},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-2990},
doi = {10.21437/INTERSPEECH.2020-2990},
timestamp = {Fri, 29 Jan 2021 17:40:16 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/GumpHG20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KhuranaLHCLMG20,
author = {Sameer Khurana and
Antoine Laurent and
Wei{-}Ning Hsu and
Jan Chorowski and
Adrian Lancucki and
Ricard Marxer and
James R. Glass},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {A Convolutional Deep Markov Model for Unsupervised Speech Representation
Learning},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {3790--3794},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-3084},
doi = {10.21437/INTERSPEECH.2020-3084},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/KhuranaLHCLMG20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-10336,
author = {Wei{-}Ning Hsu and
Ann Lee and
Gabriel Synnaeve and
Awni Y. Hannun},
title = {Semi-Supervised Speech Recognition via Local Prior Matching},
journal = {CoRR},
volume = {abs/2002.10336},
year = {2020},
url = {https://arxiv.org/abs/2002.10336},
eprinttype = {arXiv},
eprint = {2002.10336},
timestamp = {Tue, 05 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-10336.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-02547,
author = {Sameer Khurana and
Antoine Laurent and
Wei{-}Ning Hsu and
Jan Chorowski and
Adrian Lancucki and
Ricard Marxer and
James R. Glass},
title = {A Convolutional Deep Markov Model for Unsupervised Speech Representation
Learning},
journal = {CoRR},
volume = {abs/2006.02547},
year = {2020},
url = {https://arxiv.org/abs/2006.02547},
eprinttype = {arXiv},
eprint = {2006.02547},
timestamp = {Tue, 09 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-02547.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-01003,
author = {Awni Y. Hannun and
Vineel Pratap and
Jacob Kahn and
Wei{-}Ning Hsu},
title = {Differentiable Weighted Finite-State Transducers},
journal = {CoRR},
volume = {abs/2010.01003},
year = {2020},
url = {https://arxiv.org/abs/2010.01003},
eprinttype = {arXiv},
eprint = {2010.01003},
timestamp = {Tue, 05 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-01003.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2012-15454,
author = {Wei{-}Ning Hsu and
David Harwath and
Christopher Song and
James R. Glass},
title = {Text-Free Image-to-Speech Synthesis Using Learned Segmental Units},
journal = {CoRR},
volume = {abs/2012.15454},
year = {2020},
url = {https://arxiv.org/abs/2012.15454},
eprinttype = {arXiv},
eprint = {2012.15454},
timestamp = {Fri, 08 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2012-15454.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HsuZWCWWG19,
author = {Wei{-}Ning Hsu and
Yu Zhang and
Ron J. Weiss and
Yu{-}An Chung and
Yuxuan Wang and
Yonghui Wu and
James R. Glass},
title = {Disentangling Correlated Speaker and Noise for Speech Synthesis via
Data Augmentation and Adversarial Factorization},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {5901--5905},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8683561},
doi = {10.1109/ICASSP.2019.8683561},
timestamp = {Mon, 25 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HsuZWCWWG19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ChungWHZS19,
author = {Yu{-}An Chung and
Yuxuan Wang and
Wei{-}Ning Hsu and
Yu Zhang and
R. J. Skerry{-}Ryan},
title = {Semi-supervised Training for Improving Data Efficiency in End-to-end
Speech Synthesis},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {6940--6944},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8683862},
doi = {10.1109/ICASSP.2019.8683862},
timestamp = {Wed, 20 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ChungWHZS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/HsuZWZWWCJCSNP19,
author = {Wei{-}Ning Hsu and
Yu Zhang and
Ron J. Weiss and
Heiga Zen and
Yonghui Wu and
Yuxuan Wang and
Yuan Cao and
Ye Jia and
Zhifeng Chen and
Jonathan Shen and
Patrick Nguyen and
Ruoming Pang},
title = {Hierarchical Generative Modeling for Controllable Speech Synthesis},
booktitle = {7th International Conference on Learning Representations, {ICLR} 2019,
New Orleans, LA, USA, May 6-9, 2019},
publisher = {OpenReview.net},
year = {2019},
url = {https://openreview.net/forum?id=rygkk305YQ},
timestamp = {Mon, 25 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/HsuZWZWWCJCSNP19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ChungHTG19,
author = {Yu{-}An Chung and
Wei{-}Ning Hsu and
Hao Tang and
James R. Glass},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {An Unsupervised Autoregressive Model for Speech Representation Learning},
booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech
Communication Association, Graz, Austria, 15-19 September 2019},
pages = {146--150},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-1473},
doi = {10.21437/INTERSPEECH.2019-1473},
timestamp = {Fri, 29 Jan 2021 17:41:10 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/ChungHTG19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HsuHG19,
author = {Wei{-}Ning Hsu and
David Harwath and
James R. Glass},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {Transfer Learning from Audio-Visual Grounding to Speech Recognition},
booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech
Communication Association, Graz, Austria, 15-19 September 2019},
pages = {3242--3246},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-1227},
doi = {10.21437/INTERSPEECH.2019-1227},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/HsuHG19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1902-08295,
author = {Jonathan Shen and
Patrick Nguyen and
Yonghui Wu and
Zhifeng Chen and
Mia Xu Chen and
Ye Jia and
Anjuli Kannan and
Tara N. Sainath and
Yuan Cao and
Chung{-}Cheng Chiu and
Yanzhang He and
Jan Chorowski and
Smit Hinsu and
Stella Laurenzo and
James Qin and
Orhan Firat and
Wolfgang Macherey and
Suyog Gupta and
Ankur Bapna and
Shuyuan Zhang and
Ruoming Pang and
Ron J. Weiss and
Rohit Prabhavalkar and
Qiao Liang and
Benoit Jacob and
Bowen Liang and
HyoukJoong Lee and
Ciprian Chelba and
S{\'{e}}bastien Jean and
Bo Li and
Melvin Johnson and
Rohan Anil and
Rajat Tibrewal and
Xiaobing Liu and
Akiko Eriguchi and
Navdeep Jaitly and
Naveen Ari and
Colin Cherry and
Parisa Haghani and
Otavio Good and
Youlong Cheng and
Raziel Alvarez and
Isaac Caswell and
Wei{-}Ning Hsu and
Zongheng Yang and
Kuan{-}Chieh Wang and
Ekaterina Gonina and
Katrin Tomanek and
Ben Vanik and
Zelin Wu and
Llion Jones and
Mike Schuster and
Yanping Huang and
Dehao Chen and
Kazuki Irie and
George F. Foster and
John Richardson and
Klaus Macherey and
Antoine Bruguier and
Heiga Zen and
Colin Raffel and
Shankar Kumar and
Kanishka Rao and
David Rybach and
Matthew Murray and
Vijayaditya Peddinti and
Maxim Krikun and
Michiel Bacchiani and
Thomas B. Jablin and
Robert Suderman and
Ian Williams and
Benjamin Lee and
Deepti Bhatia and
Justin Carlson and
Semih Yavuz and
Yu Zhang and
Ian McGraw and
Max Galkin and
Qi Ge and
Golan Pundak and
Chad Whipkey and
Todd Wang and
Uri Alon and
Dmitry Lepikhin and
Ye Tian and
Sara Sabour and
William Chan and
Shubham Toshniwal and
Baohua Liao and
Michael Nirschl and
Pat Rondon},
title = {Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence
Modeling},
journal = {CoRR},
volume = {abs/1902.08295},
year = {2019},
url = {http://arxiv.org/abs/1902.08295},
eprinttype = {arXiv},
eprint = {1902.08295},
timestamp = {Tue, 07 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1902-08295.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-03240,
author = {Yu{-}An Chung and
Wei{-}Ning Hsu and
Hao Tang and
James R. Glass},
title = {An Unsupervised Autoregressive Model for Speech Representation Learning},
journal = {CoRR},
volume = {abs/1904.03240},
year = {2019},
url = {http://arxiv.org/abs/1904.03240},
eprinttype = {arXiv},
eprint = {1904.03240},
timestamp = {Wed, 30 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-03240.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-04355,
author = {Wei{-}Ning Hsu and
David F. Harwath and
James R. Glass},
title = {Transfer Learning from Audio-Visual Grounding to Speech Recognition},
journal = {CoRR},
volume = {abs/1907.04355},
year = {2019},
url = {http://arxiv.org/abs/1907.04355},
eprinttype = {arXiv},
eprint = {1907.04355},
timestamp = {Tue, 23 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1907-04355.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-09602,
author = {David Harwath and
Wei{-}Ning Hsu and
James R. Glass},
title = {Learning Hierarchical Discrete Linguistic Units from Visually-Grounded
Speech},
journal = {CoRR},
volume = {abs/1911.09602},
year = {2019},
url = {http://arxiv.org/abs/1911.09602},
eprinttype = {arXiv},
eprint = {1911.09602},
timestamp = {Tue, 03 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-09602.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HsuG18,
author = {Wei{-}Ning Hsu and
James R. Glass},
title = {Extracting Domain Invariant Features by Unsupervised Learning for
Robust Automatic Speech Recognition},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {5614--5618},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8462037},
doi = {10.1109/ICASSP.2018.8462037},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HsuG18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpr/ZhengWXHG18,
author = {Siqi Zheng and
Jianzong Wang and
Jing Xiao and
Wei{-}Ning Hsu and
James R. Glass},
title = {A Noise-Robust Self-Adaptive Multitarget Speaker Detection System},
booktitle = {24th International Conference on Pattern Recognition, {ICPR} 2018,
Beijing, China, August 20-24, 2018},
pages = {1068--1072},
publisher = {{IEEE} Computer Society},
year = {2018},
url = {https://doi.org/10.1109/ICPR.2018.8545395},
doi = {10.1109/ICPR.2018.8545395},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icpr/ZhengWXHG18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HsuG18,
author = {Wei{-}Ning Hsu and
James R. Glass},
editor = {B. Yegnanarayana},
title = {Scalable Factorized Hierarchical Variational Autoencoder Training},
booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech
Communication Association, Hyderabad, India, 2-6 September 2018},
pages = {1462--1466},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1034},
doi = {10.21437/INTERSPEECH.2018-1034},
timestamp = {Fri, 21 May 2021 08:16:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HsuG18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HsuTG18,
author = {Wei{-}Ning Hsu and
Hao Tang and
James R. Glass},
editor = {B. Yegnanarayana},
title = {Unsupervised Adaptation with Interpretable Disentangled Representations
for Distant Conversational Speech Recognition},
booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech
Communication Association, Hyderabad, India, 2-6 September 2018},
pages = {1576--1580},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1097},
doi = {10.21437/INTERSPEECH.2018-1097},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/HsuTG18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TangHGG18,
author = {Hao Tang and
Wei{-}Ning Hsu and
Fran{\c{c}}ois Grondin and
James R. Glass},
editor = {B. Yegnanarayana},
title = {A Study of Enhancement, Augmentation and Autoencoder Methods for Domain
Adaptation in Distant Speech Recognition},
booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech
Communication Association, Hyderabad, India, 2-6 September 2018},
pages = {2928--2932},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-2030},
doi = {10.21437/INTERSPEECH.2018-2030},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/TangHGG18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/ShonHG18,
author = {Suwon Shon and
Wei{-}Ning Hsu and
James R. Glass},
title = {Unsupervised Representation Learning of Speech for Dialect Identification},
booktitle = {2018 {IEEE} Spoken Language Technology Workshop, {SLT} 2018, Athens,
Greece, December 18-21, 2018},
pages = {105--111},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/SLT.2018.8639650},
doi = {10.1109/SLT.2018.8639650},
timestamp = {Wed, 16 Oct 2019 14:14:53 +0200},
biburl = {https://dblp.org/rec/conf/slt/ShonHG18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-02551,
author = {Wei{-}Ning Hsu and
James R. Glass},
title = {Extracting Domain Invariant Features by Unsupervised Learning for
Robust Automatic Speech Recognition},
journal = {CoRR},
volume = {abs/1803.02551},
year = {2018},
url = {http://arxiv.org/abs/1803.02551},
eprinttype = {arXiv},
eprint = {1803.02551},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1803-02551.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-03201,
author = {Wei{-}Ning Hsu and
James R. Glass},
title = {Scalable Factorized Hierarchical Variational Autoencoder Training},
journal = {CoRR},
volume = {abs/1804.03201},
year = {2018},
url = {http://arxiv.org/abs/1804.03201},
eprinttype = {arXiv},
eprint = {1804.03201},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1804-03201.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1805-11264,
author = {Wei{-}Ning Hsu and
James R. Glass},
title = {Disentangling by Partitioning: {A} Representation Learning Framework
for Multimodal Sensory Data},
journal = {CoRR},
volume = {abs/1805.11264},
year = {2018},
url = {http://arxiv.org/abs/1805.11264},
eprinttype = {arXiv},
eprint = {1805.11264},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1805-11264.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-04841,
author = {Hao Tang and
Wei{-}Ning Hsu and
Fran{\c{c}}ois Grondin and
James R. Glass},
title = {A Study of Enhancement, Augmentation, and Autoencoder Methods for
Domain Adaptation in Distant Speech Recognition},
journal = {CoRR},
volume = {abs/1806.04841},
year = {2018},
url = {http://arxiv.org/abs/1806.04841},
eprinttype = {arXiv},
eprint = {1806.04841},
timestamp = {Wed, 30 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-04841.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-04872,
author = {Wei{-}Ning Hsu and
Hao Tang and
James R. Glass},
title = {Unsupervised Adaptation with Interpretable Disentangled Representations
for Distant Conversational Speech Recognition},
journal = {CoRR},
volume = {abs/1806.04872},
year = {2018},
url = {http://arxiv.org/abs/1806.04872},
eprinttype = {arXiv},
eprint = {1806.04872},
timestamp = {Wed, 30 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-04872.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1808-10128,
author = {Yu{-}An Chung and
Yuxuan Wang and
Wei{-}Ning Hsu and
Yu Zhang and
R. J. Skerry{-}Ryan},
title = {Semi-Supervised Training for Improving Data Efficiency in End-to-End
Speech Synthesis},
journal = {CoRR},
volume = {abs/1808.10128},
year = {2018},
url = {http://arxiv.org/abs/1808.10128},
eprinttype = {arXiv},
eprint = {1808.10128},
timestamp = {Wed, 20 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1808-10128.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1809-04458,
author = {Suwon Shon and
Wei{-}Ning Hsu and
James R. Glass},
title = {Unsupervised Representation Learning of Speech for Dialect Identification},
journal = {CoRR},
volume = {abs/1809.04458},
year = {2018},
url = {http://arxiv.org/abs/1809.04458},
eprinttype = {arXiv},
eprint = {1809.04458},
timestamp = {Fri, 05 Oct 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1809-04458.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1810-07217,
author = {Wei{-}Ning Hsu and
Yu Zhang and
Ron J. Weiss and
Heiga Zen and
Yonghui Wu and
Yuxuan Wang and
Yuan Cao and
Ye Jia and
Zhifeng Chen and
Jonathan Shen and
Patrick Nguyen and
Ruoming Pang},
title = {Hierarchical Generative Modeling for Controllable Speech Synthesis},
journal = {CoRR},
volume = {abs/1810.07217},
year = {2018},
url = {http://arxiv.org/abs/1810.07217},
eprinttype = {arXiv},
eprint = {1810.07217},
timestamp = {Mon, 25 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1810-07217.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/HsuZG17,
author = {Wei{-}Ning Hsu and
Yu Zhang and
James R. Glass},
title = {Unsupervised domain adaptation for robust speech recognition via variational
autoencoder-based data augmentation},
booktitle = {2017 {IEEE} Automatic Speech Recognition and Understanding Workshop,
{ASRU} 2017, Okinawa, Japan, December 16-20, 2017},
pages = {16--23},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ASRU.2017.8268911},
doi = {10.1109/ASRU.2017.8268911},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/asru/HsuZG17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/NajafianHAG17,
author = {Maryam Najafian and
Wei{-}Ning Hsu and
Ahmed Ali and
James R. Glass},
title = {Automatic speech recognition of Arabic multi-genre broadcast media},
booktitle = {2017 {IEEE} Automatic Speech Recognition and Understanding Workshop,
{ASRU} 2017, Okinawa, Japan, December 16-20, 2017},
pages = {353--359},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ASRU.2017.8268957},
doi = {10.1109/ASRU.2017.8268957},
timestamp = {Fri, 03 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/asru/NajafianHAG17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HsuZG17,
author = {Wei{-}Ning Hsu and
Yu Zhang and
James R. Glass},
editor = {Francisco Lacerda},
title = {Learning Latent Representations for Speech Generation and Transformation},
booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech
Communication Association, Stockholm, Sweden, August 20-24, 2017},
pages = {1273--1277},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-349},
doi = {10.21437/INTERSPEECH.2017-349},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HsuZG17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/HsuZG17,
author = {Wei{-}Ning Hsu and
Yu Zhang and
James R. Glass},
editor = {Isabelle Guyon and
Ulrike von Luxburg and
Samy Bengio and
Hanna M. Wallach and
Rob Fergus and
S. V. N. Vishwanathan and
Roman Garnett},
title = {Unsupervised Learning of Disentangled and Interpretable Representations
from Sequential Data},
booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference
on Neural Information Processing Systems 2017, December 4-9, 2017,
Long Beach, CA, {USA}},
pages = {1878--1889},
year = {2017},
url = {https://proceedings.neurips.cc/paper/2017/hash/0a0a0c8aaa00ade50f74a3f0ca981ed7-Abstract.html},
timestamp = {Thu, 21 Jan 2021 13:58:27 +0100},
biburl = {https://dblp.org/rec/conf/nips/HsuZG17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HsuZG17,
author = {Wei{-}Ning Hsu and
Yu Zhang and
James R. Glass},
title = {Learning Latent Representations for Speech Generation and Transformation},
journal = {CoRR},
volume = {abs/1704.04222},
year = {2017},
url = {http://arxiv.org/abs/1704.04222},
eprinttype = {arXiv},
eprint = {1704.04222},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HsuZG17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HsuZG17aa,
author = {Wei{-}Ning Hsu and
Yu Zhang and
James R. Glass},
title = {Unsupervised Domain Adaptation for Robust Speech Recognition via Variational
Autoencoder-Based Data Augmentation},
journal = {CoRR},
volume = {abs/1707.06265},
year = {2017},
url = {http://arxiv.org/abs/1707.06265},
eprinttype = {arXiv},
eprint = {1707.06265},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HsuZG17aa.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1709-07902,
author = {Wei{-}Ning Hsu and
Yu Zhang and
James R. Glass},
title = {Unsupervised Learning of Disentangled and Interpretable Representations
from Sequential Data},
journal = {CoRR},
volume = {abs/1709.07902},
year = {2017},
url = {http://arxiv.org/abs/1709.07902},
eprinttype = {arXiv},
eprint = {1709.07902},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1709-07902.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/coling/RomeoMBMBHZMG16,
author = {Salvatore Romeo and
Giovanni Da San Martino and
Alberto Barr{\'{o}}n{-}Cede{\~{n}}o and
Alessandro Moschitti and
Yonatan Belinkov and
Wei{-}Ning Hsu and
Yu Zhang and
Mitra Mohtarami and
James R. Glass},
editor = {Nicoletta Calzolari and
Yuji Matsumoto and
Rashmi Prasad},
title = {Neural Attention for Learning to Rank Questions in Community Question
Answering},
booktitle = {{COLING} 2016, 26th International Conference on Computational Linguistics,
Proceedings of the Conference: Technical Papers, December 11-16, 2016,
Osaka, Japan},
pages = {1734--1745},
publisher = {{ACL}},
year = {2016},
url = {https://aclanthology.org/C16-1163/},
timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/coling/RomeoMBMBHZMG16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HsuZLG16,
author = {Wei{-}Ning Hsu and
Yu Zhang and
Ann Lee and
James R. Glass},
editor = {Nelson Morgan},
title = {Exploiting Depth and Highway Connections in Convolutional Recurrent
Deep Neural Networks for Speech Recognition},
booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech
Communication Association, San Francisco, CA, USA, September 8-12,
2016},
pages = {395--399},
publisher = {{ISCA}},
year = {2016},
url = {https://doi.org/10.21437/Interspeech.2016-515},
doi = {10.21437/INTERSPEECH.2016-515},
timestamp = {Mon, 26 Jun 2023 16:43:56 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HsuZLG16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/semeval/MohtaramiBHZLBC16,
author = {Mitra Mohtarami and
Yonatan Belinkov and
Wei{-}Ning Hsu and
Yu Zhang and
Tao Lei and
Kfir Bar and
Scott Cyphers and
James R. Glass},
editor = {Steven Bethard and
Daniel M. Cer and
Marine Carpuat and
David Jurgens and
Preslav Nakov and
Torsten Zesch},
title = {{SLS} at SemEval-2016 Task 3: Neural-based Approaches for Ranking
in Community Question Answering},
booktitle = {Proceedings of the 10th International Workshop on Semantic Evaluation,
SemEval@NAACL-HLT 2016, San Diego, CA, USA, June 16-17, 2016},
pages = {828--835},
publisher = {The Association for Computer Linguistics},
year = {2016},
url = {https://doi.org/10.18653/v1/s16-1128},
doi = {10.18653/V1/S16-1128},
timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/semeval/MohtaramiBHZLBC16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/HanaiHG16,
author = {Tuka Al Hanai and
Wei{-}Ning Hsu and
James R. Glass},
title = {Development of the {MIT} {ASR} system for the 2016 Arabic Multi-genre
Broadcast Challenge},
booktitle = {2016 {IEEE} Spoken Language Technology Workshop, {SLT} 2016, San Diego,
CA, USA, December 13-16, 2016},
pages = {299--304},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/SLT.2016.7846280},
doi = {10.1109/SLT.2016.7846280},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/slt/HanaiHG16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/HsuZG16,
author = {Wei{-}Ning Hsu and
Yu Zhang and
James R. Glass},
title = {A prioritized grid long short-term memory {RNN} for speech recognition},
booktitle = {2016 {IEEE} Spoken Language Technology Workshop, {SLT} 2016, San Diego,
CA, USA, December 13-16, 2016},
pages = {467--473},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/SLT.2016.7846305},
doi = {10.1109/SLT.2016.7846305},
timestamp = {Thu, 07 Jun 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/slt/HsuZG16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HsuZG16,
author = {Wei{-}Ning Hsu and
Yu Zhang and
James R. Glass},
title = {Recurrent Neural Network Encoder with Attention for Community Question
Answering},
journal = {CoRR},
volume = {abs/1603.07044},
year = {2016},
url = {http://arxiv.org/abs/1603.07044},
eprinttype = {arXiv},
eprint = {1603.07044},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HsuZG16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/HsuL15,
author = {Wei{-}Ning Hsu and
Hsuan{-}Tien Lin},
editor = {Blai Bonet and
Sven Koenig},
title = {Active Learning by Learning},
booktitle = {Proceedings of the Twenty-Ninth {AAAI} Conference on Artificial Intelligence,
January 25-30, 2015, Austin, Texas, {USA}},
pages = {2659--2665},
publisher = {{AAAI} Press},
year = {2015},
url = {https://doi.org/10.1609/aaai.v29i1.9597},
doi = {10.1609/AAAI.V29I1.9597},
timestamp = {Mon, 18 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/HsuL15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ChungHLL15,
author = {Cheng{-}Tao Chung and
Wei{-}Ning Hsu and
Cheng{-}Yi Lee and
Lin{-}Shan Lee},
title = {Enhancing automatically discovered multi-level acoustic patterns considering
context consistency with applications in spoken term detection},
booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia,
April 19-24, 2015},
pages = {5231--5235},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ICASSP.2015.7178969},
doi = {10.1109/ICASSP.2015.7178969},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ChungHLL15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ChungHLL15,
author = {Cheng{-}Tao Chung and
Wei{-}Ning Hsu and
Cheng{-}Yi Lee and
Lin{-}Shan Lee},
title = {Enhancing Automatically Discovered Multi-level Acoustic Patterns Considering
Context Consistency With Applications in Spoken Term Detection},
journal = {CoRR},
volume = {abs/1509.02217},
year = {2015},
url = {http://arxiv.org/abs/1509.02217},
eprinttype = {arXiv},
eprint = {1509.02217},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ChungHLL15.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 01:55 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:
