Audio Model¶

@inproceedings{gong2021astaudiospectrogramtransformer,
  author = {Gong, Yuan and Chung, Yu-An and Glass, James},
  booktitle = {Interspeech 2021},
  collection = {interspeech_2021},
  doi = {10.21437/interspeech.2021-698},
  month = {Aug},
  pages = {571–575},
  publisher = {ISCA},
  series = {interspeech_2021},
  title = {AST: Audio Spectrogram Transformer},
  url = {https://doi.org/10.21437/interspeech.2021-698},
  year = {2021},
}

@inproceedings{wu2021performanceefficiencytradeoffsunsupervisedpretraining,
  author = {Wu, Felix and Kim, Kwangyoun and Pan, Jing and Han, Kyu J. and Weinberger, Kilian Q. and Artzi, Yoav},
  booktitle = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  doi = {10.1109/icassp43922.2022.9747432},
  month = {May},
  pages = {7667–7671},
  publisher = {IEEE},
  title = {Performance-Efficiency Trade-Offs in Unsupervised Pre-Training for Speech Recognition},
  url = {https://doi.org/10.1109/icassp43922.2022.9747432},
  year = {2022},
}

@inproceedings{wu2021performanceefficiencytradeoffsunsupervisedpretraining,
  author = {Wu, Felix and Kim, Kwangyoun and Pan, Jing and Han, Kyu J. and Weinberger, Kilian Q. and Artzi, Yoav},
  booktitle = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  doi = {10.1109/icassp43922.2022.9747432},
  month = {May},
  pages = {7667–7671},
  publisher = {IEEE},
  title = {Performance-Efficiency Trade-Offs in Unsupervised Pre-Training for Speech Recognition},
  url = {https://doi.org/10.1109/icassp43922.2022.9747432},
  year = {2022},
}

@inproceedings{wu2021performanceefficiencytradeoffsunsupervisedpretraining,
  author = {Wu, Felix and Kim, Kwangyoun and Pan, Jing and Han, Kyu J. and Weinberger, Kilian Q. and Artzi, Yoav},
  booktitle = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  doi = {10.1109/icassp43922.2022.9747432},
  month = {May},
  pages = {7667–7671},
  publisher = {IEEE},
  title = {Performance-Efficiency Trade-Offs in Unsupervised Pre-Training for Speech Recognition},
  url = {https://doi.org/10.1109/icassp43922.2022.9747432},
  year = {2022},
}

@inproceedings{baevski2022data2vecgeneralframeworkselfsupervised,
  archiveprefix = {arXiv},
  author = {Alexei Baevski and Wei-Ning Hsu and Qiantong Xu and Arun Babu and Jiatao Gu and Michael Auli},
  booktitle = {ICML},
  eprint = {2202.03555},
  pages = {1298-1312},
  title = {data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language},
  url = {https://proceedings.mlr.press/v162/baevski22a.html},
  year = {2022},
}

@inproceedings{baevski2022data2vecgeneralframeworkselfsupervised,
  archiveprefix = {arXiv},
  author = {Alexei Baevski and Wei-Ning Hsu and Qiantong Xu and Arun Babu and Jiatao Gu and Michael Auli},
  booktitle = {ICML},
  eprint = {2202.03555},
  pages = {1298-1312},
  title = {data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language},
  url = {https://proceedings.mlr.press/v162/baevski22a.html},
  year = {2022},
}

@article{défossez2022highfidelityneuralaudio,
  archiveprefix = {arXiv},
  author = {Alexandre D{\'e}fossez and Jade Copet and Gabriel Synnaeve and Yossi Adi},
  eprint = {2210.13438},
  issn = {2835-8856},
  journal = {Transactions on Machine Learning Research},
  note = {Featured Certification, Reproducibility Certification},
  title = {High Fidelity Neural Audio Compression},
  url = {https://openreview.net/forum?id=ivCd8z8zR2},
  year = {2023},
}

@article{hsu2021hubertselfsupervisedspeechrepresentation,
  author = {Hsu, Wei-Ning and Bolte, Benjamin and Tsai, Yao-Hung Hubert and Lakhotia, Kushal and Salakhutdinov, Ruslan and Mohamed, Abdelrahman},
  doi = {10.1109/taslp.2021.3122291},
  issn = {2329-9304},
  journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  pages = {3451–3460},
  publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
  title = {HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units},
  url = {https://doi.org/10.1109/taslp.2021.3122291},
  volume = {29},
  year = {2021},
}

@article{hsu2021hubertselfsupervisedspeechrepresentation,
  author = {Hsu, Wei-Ning and Bolte, Benjamin and Tsai, Yao-Hung Hubert and Lakhotia, Kushal and Salakhutdinov, Ruslan and Mohamed, Abdelrahman},
  doi = {10.1109/taslp.2021.3122291},
  issn = {2329-9304},
  journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  pages = {3451–3460},
  publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
  title = {HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units},
  url = {https://doi.org/10.1109/taslp.2021.3122291},
  volume = {29},
  year = {2021},
}

@article{pratap2023scalingspeechtechnology1000,
  archiveprefix = {arXiv},
  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},
  eprint = {2305.13516},
  journal = {J. Mach. Learn. Res.},
  pages = {97:1-97:52},
  title = {Scaling Speech Technology to 1, 000+ Languages},
  url = {https://jmlr.org/papers/v25/23-1318.html},
  volume = {25},
  year = {2024},
}

@article{pratap2023scalingspeechtechnology1000,
  archiveprefix = {arXiv},
  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},
  eprint = {2305.13516},
  journal = {J. Mach. Learn. Res.},
  pages = {97:1-97:52},
  title = {Scaling Speech Technology to 1, 000+ Languages},
  url = {https://jmlr.org/papers/v25/23-1318.html},
  volume = {25},
  year = {2024},
}

@article{pratap2023scalingspeechtechnology1000,
  archiveprefix = {arXiv},
  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},
  eprint = {2305.13516},
  journal = {J. Mach. Learn. Res.},
  pages = {97:1-97:52},
  title = {Scaling Speech Technology to 1, 000+ Languages},
  url = {https://jmlr.org/papers/v25/23-1318.html},
  volume = {25},
  year = {2024},
}

@misc{communication2023seamlessmultilingualexpressivestreaming,
  doi = {10.48550/arXiv.2312.05187},
  title = {Seamless: Multilingual Expressive and Streaming Speech Translation},
  author = {Seamless Communication and Loïc Barrault and Yu-An Chung and Mariano Coria Meglioli and David Dale and Ning Dong and Mark Duppenthaler and Paul-Ambroise Duquenne and Brian Ellis and Hady Elsahar and Justin Haaheim and John Hoffman and Min-Jae Hwang and Hirofumi Inaguma and Christopher Klaiber and Ilia Kulikov and Pengwei Li and Daniel Licht and Jean Maillard and Ruslan Mavlyutov and Alice Rakotoarison and Kaushik Ram Sadagopan and Abinesh Ramakrishnan and Tuan Tran and Guillaume Wenzek and Yilin Yang and Ethan Ye and Ivan Evtimov and Pierre Fernandez and Cynthia Gao and Prangthip Hansanti and Elahe Kalbassi and Amanda Kallet and Artyom Kozhevnikov and Gabriel Mejia Gonzalez and Robin San Roman and Christophe Touret and Corinne Wong and Carleigh Wood and Bokai Yu and Pierre Andrews and Can Balioglu and Peng-Jen Chen and Marta R. Costa-jussà and Maha Elbayad and Hongyu Gong and Francisco Guzmán and Kevin Heffernan and Somya Jain and Justine Kao and Ann Lee and Xutai Ma and Alex Mourachko and Benjamin Peloquin and Juan Pino and Sravya Popuri and Christophe Ropers and Safiyyah Saleem and Holger Schwenk and Anna Sun and Paden Tomasello and Changhan Wang and Jeff Wang and Skyler Wang and Mary Williamson},
  year = {2023},
  eprint = {2312.05187},
  archivePrefix = {arXiv},
  primaryClass = {cs.CL},
  url = {https://arxiv.org/abs/2312.05187},
}

@inproceedings{baevski2020wav2vec20frameworkselfsupervised,
  archiveprefix = {arXiv},
  author = {Alexei Baevski and Yuhao Zhou and Abdelrahman Mohamed and Michael Auli},
  booktitle = {NeurIPS},
  eprint = {2006.11477},
  title = {wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations},
  url = {https://proceedings.neurips.cc/paper/2020/hash/92d1e1eb1cd6f9fba3227870bb6d7f07-Abstract.html},
  year = {2020},
}

@inproceedings{baevski2020wav2vec20frameworkselfsupervised,
  archiveprefix = {arXiv},
  author = {Alexei Baevski and Yuhao Zhou and Abdelrahman Mohamed and Michael Auli},
  booktitle = {NeurIPS},
  eprint = {2006.11477},
  title = {wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations},
  url = {https://proceedings.neurips.cc/paper/2020/hash/92d1e1eb1cd6f9fba3227870bb6d7f07-Abstract.html},
  year = {2020},
}

@inproceedings{baevski2020wav2vec20frameworkselfsupervised,
  archiveprefix = {arXiv},
  author = {Alexei Baevski and Yuhao Zhou and Abdelrahman Mohamed and Michael Auli},
  booktitle = {NeurIPS},
  eprint = {2006.11477},
  title = {wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations},
  url = {https://proceedings.neurips.cc/paper/2020/hash/92d1e1eb1cd6f9fba3227870bb6d7f07-Abstract.html},
  year = {2020},
}

@inproceedings{conneau2020unsupervisedcrosslingualrepresentationlearning,
  author = {Conneau, Alexis and Baevski, Alexei and Collobert, Ronan and Mohamed, Abdelrahman and Auli, Michael},
  booktitle = {Interspeech 2021},
  collection = {interspeech_2021},
  doi = {10.21437/interspeech.2021-329},
  month = {Aug},
  pages = {2426–2430},
  publisher = {ISCA},
  series = {interspeech_2021},
  title = {Unsupervised Cross-Lingual Representation Learning for Speech Recognition},
  url = {https://doi.org/10.21437/interspeech.2021-329},
  year = {2021},
}

@inproceedings{baevski2020wav2vec20frameworkselfsupervised,
  archiveprefix = {arXiv},
  author = {Alexei Baevski and Yuhao Zhou and Abdelrahman Mohamed and Michael Auli},
  booktitle = {NeurIPS},
  eprint = {2006.11477},
  title = {wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations},
  url = {https://proceedings.neurips.cc/paper/2020/hash/92d1e1eb1cd6f9fba3227870bb6d7f07-Abstract.html},
  year = {2020},
}

@inproceedings{babu2021xlsrselfsupervisedcrosslingualspeech,
  author = {Babu, Arun and Wang, Changhan and Tjandra, Andros and Lakhotia, Kushal and Xu, Qiantong and Goyal, Naman and Singh, Kritika and von Platen, Patrick and Saraf, Yatharth and Pino, Juan and Baevski, Alexei and Conneau, Alexis and Auli, Michael},
  booktitle = {Interspeech 2022},
  collection = {interspeech_2022},
  doi = {10.21437/interspeech.2022-143},
  month = {Sept},
  pages = {2278–2282},
  publisher = {ISCA},
  series = {interspeech_2022},
  title = {XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale},
  url = {https://doi.org/10.21437/interspeech.2022-143},
  year = {2022},
}

@inproceedings{babu2021xlsrselfsupervisedcrosslingualspeech,
  author = {Babu, Arun and Wang, Changhan and Tjandra, Andros and Lakhotia, Kushal and Xu, Qiantong and Goyal, Naman and Singh, Kritika and von Platen, Patrick and Saraf, Yatharth and Pino, Juan and Baevski, Alexei and Conneau, Alexis and Auli, Michael},
  booktitle = {Interspeech 2022},
  collection = {interspeech_2022},
  doi = {10.21437/interspeech.2022-143},
  month = {Sept},
  pages = {2278–2282},
  publisher = {ISCA},
  series = {interspeech_2022},
  title = {XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale},
  url = {https://doi.org/10.21437/interspeech.2022-143},
  year = {2022},
}

@inproceedings{babu2021xlsrselfsupervisedcrosslingualspeech,
  author = {Babu, Arun and Wang, Changhan and Tjandra, Andros and Lakhotia, Kushal and Xu, Qiantong and Goyal, Naman and Singh, Kritika and von Platen, Patrick and Saraf, Yatharth and Pino, Juan and Baevski, Alexei and Conneau, Alexis and Auli, Michael},
  booktitle = {Interspeech 2022},
  collection = {interspeech_2022},
  doi = {10.21437/interspeech.2022-143},
  month = {Sept},
  pages = {2278–2282},
  publisher = {ISCA},
  series = {interspeech_2022},
  title = {XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale},
  url = {https://doi.org/10.21437/interspeech.2022-143},
  year = {2022},
}

@inproceedings{babu2021xlsrselfsupervisedcrosslingualspeech,
  author = {Babu, Arun and Wang, Changhan and Tjandra, Andros and Lakhotia, Kushal and Xu, Qiantong and Goyal, Naman and Singh, Kritika and von Platen, Patrick and Saraf, Yatharth and Pino, Juan and Baevski, Alexei and Conneau, Alexis and Auli, Michael},
  booktitle = {Interspeech 2022},
  collection = {interspeech_2022},
  doi = {10.21437/interspeech.2022-143},
  month = {Sept},
  pages = {2278–2282},
  publisher = {ISCA},
  series = {interspeech_2022},
  title = {XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale},
  url = {https://doi.org/10.21437/interspeech.2022-143},
  year = {2022},
}

@inproceedings{hershey2017cnn,
    author = {Hershey, Shawn and Chaudhuri, Sourish and Ellis, Daniel P. W. and Gemmeke, Jort F. and Jansen, Aren and Moore, R. Channing and Plakal, Manoj and Platt, Devin and Saurous, Rif A. and Seybold, Bryan and Slaney, Malcolm and Weiss, Ron J. and Wilson, Kevin},
    title = {CNN architectures for large-scale audio classification},
    year = {2017},
    publisher = {IEEE Press},
    url = {https://doi.org/10.1109/ICASSP.2017.7952132},
    doi = {10.1109/ICASSP.2017.7952132},
    booktitle = {2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
    pages = {131–135},
    numpages = {5},
    location = {New Orleans, LA, USA}
}

@inproceedings{audioset,
  title={Audio set: An ontology and human-labeled dataset for audio events},
  author={Gemmeke, Jort F and Ellis, Daniel PW and Freedman, Dylan and Jansen, Aren and Lawrence, Wade and Moore, R Channing and Plakal, Manoj and Ritter, Marvin},
  booktitle={2017 IEEE international conference on acoustics, speech and signal processing (ICASSP)},
  pages={776--780},
  year={2017},
  organization={IEEE}
}

@article{Qwen3-TTS,
  title={Qwen3-TTS Technical Report},
  author={Hangrui Hu and Xinfa Zhu and Ting He and Dake Guo and Bin Zhang and Xiong Wang and Zhifang Guo and Ziyue Jiang and Hongkun Hao and Zishan Guo and Xinyu Zhang and Pei Zhang and Baosong Yang and Jin Xu and Jingren Zhou and Junyang Lin},
  journal={arXiv preprint arXiv:2601.15621},
  year={2026}
}

@article{Qwen3-TTS,
  title={Qwen3-TTS Technical Report},
  author={Hangrui Hu and Xinfa Zhu and Ting He and Dake Guo and Bin Zhang and Xiong Wang and Zhifang Guo and Ziyue Jiang and Hongkun Hao and Zishan Guo and Xinyu Zhang and Pei Zhang and Baosong Yang and Jin Xu and Jingren Zhou and Junyang Lin},
  journal={arXiv preprint arXiv:2601.15621},
  year={2026}
}

@inproceedings{ao2022speecht5unifiedmodalencoderdecoderpretraining,
  address = {Dublin, Ireland},
  author = {Ao, Junyi and Wang, Rui and Zhou, Long and Wang, Chengyi and Ren, Shuo and Wu, Yu and Liu, Shujie and Ko, Tom and Li, Qing and Zhang, Yu and Wei, Zhihua and Qian, Yao and Li, Jinyu and Wei, Furu},
  booktitle = {Proceedings of the 60th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2022.acl-long.393},
  editor = {Muresan, Smaranda and Nakov, Preslav and Villavicencio, Aline},
  month = {may},
  pages = {5723--5738},
  publisher = {Association for Computational Linguistics},
  title = {{S}peech{T}5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing},
  url = {https://aclanthology.org/2022.acl-long.393/},
  year = {2022},
}

@inproceedings{chen2021unispeechsatuniversalspeechrepresentation,
  author = {Chen, Sanyuan and Wu, Yu and Wang, Chengyi and Chen, Zhengyang and Chen, Zhuo and Liu, Shujie and Wu, Jian and Qian, Yao and Wei, Furu and Li, Jinyu and Yu, Xiangzhan},
  booktitle = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  doi = {10.1109/icassp43922.2022.9747077},
  month = {May},
  pages = {6152–6156},
  publisher = {IEEE},
  title = {Unispeech-Sat: Universal Speech Representation Learning With Speaker Aware Pre-Training},
  url = {https://doi.org/10.1109/icassp43922.2022.9747077},
  year = {2022},
}

@article{Chen_2022,
   title={WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing},
   volume={16},
   ISSN={1941-0484},
   url={http://dx.doi.org/10.1109/JSTSP.2022.3188113},
   DOI={10.1109/jstsp.2022.3188113},
   number={6},
   journal={IEEE Journal of Selected Topics in Signal Processing},
   publisher={Institute of Electrical and Electronics Engineers (IEEE)},
   author={Chen, Sanyuan and Wang, Chengyi and Chen, Zhengyang and Wu, Yu and Liu, Shujie and Chen, Zhuo and Li, Jinyu and Kanda, Naoyuki and Yoshioka, Takuya and Xiao, Xiong and Wu, Jian and Zhou, Long and Ren, Shuo and Qian, Yanmin and Qian, Yao and Wu, Jian and Zeng, Michael and Yu, Xiangzhan and Wei, Furu},
   year={2022},
   month=oct, pages={1505–1518} }

@article{Chen_2022,
   title={WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing},
   volume={16},
   ISSN={1941-0484},
   url={http://dx.doi.org/10.1109/JSTSP.2022.3188113},
   DOI={10.1109/jstsp.2022.3188113},
   number={6},
   journal={IEEE Journal of Selected Topics in Signal Processing},
   publisher={Institute of Electrical and Electronics Engineers (IEEE)},
   author={Chen, Sanyuan and Wang, Chengyi and Chen, Zhengyang and Wu, Yu and Liu, Shujie and Chen, Zhuo and Li, Jinyu and Kanda, Naoyuki and Yoshioka, Takuya and Xiao, Xiong and Wu, Jian and Zhou, Long and Ren, Shuo and Qian, Yanmin and Qian, Yao and Wu, Jian and Zeng, Michael and Yu, Xiangzhan and Wei, Furu},
   year={2022},
   month=oct, pages={1505–1518} }

@article{Chen_2022,
   title={WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing},
   volume={16},
   ISSN={1941-0484},
   url={http://dx.doi.org/10.1109/JSTSP.2022.3188113},
   DOI={10.1109/jstsp.2022.3188113},
   number={6},
   journal={IEEE Journal of Selected Topics in Signal Processing},
   publisher={Institute of Electrical and Electronics Engineers (IEEE)},
   author={Chen, Sanyuan and Wang, Chengyi and Chen, Zhengyang and Wu, Yu and Liu, Shujie and Chen, Zhuo and Li, Jinyu and Kanda, Naoyuki and Yoshioka, Takuya and Xiao, Xiong and Wu, Jian and Zhou, Long and Ren, Shuo and Qian, Yanmin and Qian, Yao and Wu, Jian and Zeng, Michael and Yu, Xiangzhan and Wei, Furu},
   year={2022},
   month=oct, pages={1505–1518} }

@article{Chen_2022,
   title={WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing},
   volume={16},
   ISSN={1941-0484},
   url={http://dx.doi.org/10.1109/JSTSP.2022.3188113},
   DOI={10.1109/jstsp.2022.3188113},
   number={6},
   journal={IEEE Journal of Selected Topics in Signal Processing},
   publisher={Institute of Electrical and Electronics Engineers (IEEE)},
   author={Chen, Sanyuan and Wang, Chengyi and Chen, Zhengyang and Wu, Yu and Liu, Shujie and Chen, Zhuo and Li, Jinyu and Kanda, Naoyuki and Yoshioka, Takuya and Xiao, Xiong and Wu, Jian and Zhou, Long and Ren, Shuo and Qian, Yanmin and Qian, Yao and Wu, Jian and Zeng, Michael and Yu, Xiangzhan and Wei, Furu},
   year={2022},
   month=oct, pages={1505–1518} }

@article{Chen_2022,
   title={WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing},
   volume={16},
   ISSN={1941-0484},
   url={http://dx.doi.org/10.1109/JSTSP.2022.3188113},
   DOI={10.1109/jstsp.2022.3188113},
   number={6},
   journal={IEEE Journal of Selected Topics in Signal Processing},
   publisher={Institute of Electrical and Electronics Engineers (IEEE)},
   author={Chen, Sanyuan and Wang, Chengyi and Chen, Zhengyang and Wu, Yu and Liu, Shujie and Chen, Zhuo and Li, Jinyu and Kanda, Naoyuki and Yoshioka, Takuya and Xiao, Xiong and Wu, Jian and Zhou, Long and Ren, Shuo and Qian, Yanmin and Qian, Yao and Wu, Jian and Zeng, Michael and Yu, Xiangzhan and Wei, Furu},
   year={2022},
   month=oct, pages={1505–1518} }

@article{Chen_2022,
   title={WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing},
   volume={16},
   ISSN={1941-0484},
   url={http://dx.doi.org/10.1109/JSTSP.2022.3188113},
   DOI={10.1109/jstsp.2022.3188113},
   number={6},
   journal={IEEE Journal of Selected Topics in Signal Processing},
   publisher={Institute of Electrical and Electronics Engineers (IEEE)},
   author={Chen, Sanyuan and Wang, Chengyi and Chen, Zhengyang and Wu, Yu and Liu, Shujie and Chen, Zhuo and Li, Jinyu and Kanda, Naoyuki and Yoshioka, Takuya and Xiao, Xiong and Wu, Jian and Zhou, Long and Ren, Shuo and Qian, Yanmin and Qian, Yao and Wu, Jian and Zeng, Michael and Yu, Xiangzhan and Wei, Furu},
   year={2022},
   month=oct, pages={1505–1518} }

@article{Chen_2022,
   title={WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing},
   volume={16},
   ISSN={1941-0484},
   url={http://dx.doi.org/10.1109/JSTSP.2022.3188113},
   DOI={10.1109/jstsp.2022.3188113},
   number={6},
   journal={IEEE Journal of Selected Topics in Signal Processing},
   publisher={Institute of Electrical and Electronics Engineers (IEEE)},
   author={Chen, Sanyuan and Wang, Chengyi and Chen, Zhengyang and Wu, Yu and Liu, Shujie and Chen, Zhuo and Li, Jinyu and Kanda, Naoyuki and Yoshioka, Takuya and Xiao, Xiong and Wu, Jian and Zhou, Long and Ren, Shuo and Qian, Yanmin and Qian, Yao and Wu, Jian and Zeng, Michael and Yu, Xiangzhan and Wei, Furu},
   year={2022},
   month=oct, pages={1505–1518} }

@inproceedings{dinkel2023scaling,
    title={Scaling up masked audio encoder learning for general audio classification},
    author={Dinkel, Heinrich and Yan, Zhiyong and Wang, Yongqing and Zhang, Junbo and Wang, Yujun and Wang, Bin},
    booktitle={Interspeech 2024},
    year={2024},
    url={https://arxiv.org/abs/2406.06992}
}

@inproceedings{dinkel2023scaling,
    title={Scaling up masked audio encoder learning for general audio classification},
    author={Dinkel, Heinrich and Yan, Zhiyong and Wang, Yongqing and Zhang, Junbo and Wang, Yujun and Wang, Bin},
    booktitle={Interspeech 2024},
    year={2024},
    url={https://arxiv.org/abs/2406.06992}
}

@inproceedings{dinkel2023scaling,
    title={Scaling up masked audio encoder learning for general audio classification},
    author={Dinkel, Heinrich and Yan, Zhiyong and Wang, Yongqing and Zhang, Junbo and Wang, Yujun and Wang, Bin},
    booktitle={Interspeech 2024},
    year={2024},
    url={https://arxiv.org/abs/2406.06992}
}

@inproceedings{radford2022robustspeechrecognitionlargescale,
  archiveprefix = {arXiv},
  author = {Alec Radford and Jong Wook Kim and Tao Xu and Greg Brockman and Christine McLeavey and Ilya Sutskever},
  booktitle = {Proceedings of the 40th International Conference on Machine Learning},
  eprint = {2212.04356},
  pages = {28492--28518},
  primaryclass = {eess.AS},
  publisher = {PMLR},
  series = {Proceedings of Machine Learning Research},
  title = {Robust Speech Recognition via Large-Scale Weak Supervision},
  url = {https://proceedings.mlr.press/v202/radford23a.html},
  volume = {202},
  year = {2023},
}

@inproceedings{radford2022robustspeechrecognitionlargescale,
  archiveprefix = {arXiv},
  author = {Alec Radford and Jong Wook Kim and Tao Xu and Greg Brockman and Christine McLeavey and Ilya Sutskever},
  booktitle = {Proceedings of the 40th International Conference on Machine Learning},
  eprint = {2212.04356},
  pages = {28492--28518},
  primaryclass = {eess.AS},
  publisher = {PMLR},
  series = {Proceedings of Machine Learning Research},
  title = {Robust Speech Recognition via Large-Scale Weak Supervision},
  url = {https://proceedings.mlr.press/v202/radford23a.html},
  volume = {202},
  year = {2023},
}

@inproceedings{radford2022robustspeechrecognitionlargescale,
  archiveprefix = {arXiv},
  author = {Alec Radford and Jong Wook Kim and Tao Xu and Greg Brockman and Christine McLeavey and Ilya Sutskever},
  booktitle = {Proceedings of the 40th International Conference on Machine Learning},
  eprint = {2212.04356},
  pages = {28492--28518},
  primaryclass = {eess.AS},
  publisher = {PMLR},
  series = {Proceedings of Machine Learning Research},
  title = {Robust Speech Recognition via Large-Scale Weak Supervision},
  url = {https://proceedings.mlr.press/v202/radford23a.html},
  volume = {202},
  year = {2023},
}

@inproceedings{radford2022robustspeechrecognitionlargescale,
  archiveprefix = {arXiv},
  author = {Alec Radford and Jong Wook Kim and Tao Xu and Greg Brockman and Christine McLeavey and Ilya Sutskever},
  booktitle = {Proceedings of the 40th International Conference on Machine Learning},
  eprint = {2212.04356},
  pages = {28492--28518},
  primaryclass = {eess.AS},
  publisher = {PMLR},
  series = {Proceedings of Machine Learning Research},
  title = {Robust Speech Recognition via Large-Scale Weak Supervision},
  url = {https://proceedings.mlr.press/v202/radford23a.html},
  volume = {202},
  year = {2023},
}

@inproceedings{radford2022robustspeechrecognitionlargescale,
  archiveprefix = {arXiv},
  author = {Alec Radford and Jong Wook Kim and Tao Xu and Greg Brockman and Christine McLeavey and Ilya Sutskever},
  booktitle = {Proceedings of the 40th International Conference on Machine Learning},
  eprint = {2212.04356},
  pages = {28492--28518},
  primaryclass = {eess.AS},
  publisher = {PMLR},
  series = {Proceedings of Machine Learning Research},
  title = {Robust Speech Recognition via Large-Scale Weak Supervision},
  url = {https://proceedings.mlr.press/v202/radford23a.html},
  volume = {202},
  year = {2023},
}

@inproceedings{radford2022robustspeechrecognitionlargescale,
  archiveprefix = {arXiv},
  author = {Alec Radford and Jong Wook Kim and Tao Xu and Greg Brockman and Christine McLeavey and Ilya Sutskever},
  booktitle = {Proceedings of the 40th International Conference on Machine Learning},
  eprint = {2212.04356},
  pages = {28492--28518},
  primaryclass = {eess.AS},
  publisher = {PMLR},
  series = {Proceedings of Machine Learning Research},
  title = {Robust Speech Recognition via Large-Scale Weak Supervision},
  url = {https://proceedings.mlr.press/v202/radford23a.html},
  volume = {202},
  year = {2023},
}

@inproceedings{wang2022CRL,
    title={Learning Representations for New Sound Classes With Continual Self-Supervised Learning},
    author={Zhepei Wang, Cem Subakan, Xilin Jiang, Junkai Wu, Efthymios Tzinis, Mirco Ravanelli, Paris Smaragdis},
    year={2022},
    booktitle={Accepted to IEEE Signal Processing Letters}
}

@inproceedings{lugosch2022pseudolabelingmassivelymultilingualspeech,
  author = {Lugosch, Loren and Likhomanenko, Tatiana and Synnaeve, Gabriel and Collobert, Ronan},
  booktitle = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  doi = {10.1109/icassp43922.2022.9746832},
  month = {May},
  pages = {7687–7691},
  publisher = {IEEE},
  title = {Pseudo-Labeling for Massively Multilingual Speech Recognition},
  url = {https://doi.org/10.1109/icassp43922.2022.9746832},
  year = {2022},
}

@inproceedings{babu2021xlsrselfsupervisedcrosslingualspeech,
  author = {Babu, Arun and Wang, Changhan and Tjandra, Andros and Lakhotia, Kushal and Xu, Qiantong and Goyal, Naman and Singh, Kritika and von Platen, Patrick and Saraf, Yatharth and Pino, Juan and Baevski, Alexei and Conneau, Alexis and Auli, Michael},
  booktitle = {Interspeech 2022},
  collection = {interspeech_2022},
  doi = {10.21437/interspeech.2022-143},
  month = {Sept},
  pages = {2278–2282},
  publisher = {ISCA},
  series = {interspeech_2022},
  title = {XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale},
  url = {https://doi.org/10.21437/interspeech.2022-143},
  year = {2022},
}