{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:20Z","timestamp":1775230160412,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414460","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6533-6537","source":"Crossref","is-referenced-by-count":76,"title":["Hubert: How Much Can a Bad Teacher Benefit ASR Pre-Training?"],"prefix":"10.1109","author":[{"given":"Wei-Ning","family":"Hsu","sequence":"first","affiliation":[]},{"given":"Yao-Hung Hubert","family":"Tsai","sequence":"additional","affiliation":[]},{"given":"Benjamin","family":"Bolte","sequence":"additional","affiliation":[]},{"given":"Ruslan","family":"Salakhutdinov","sequence":"additional","affiliation":[]},{"given":"Abdelrahman","family":"Mohamed","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Scikit-learn: Machine learning in python","author":"pedregosa","year":"2011","journal-title":"The Journal of Machine Learning Research"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053541"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.213"},{"key":"ref30","article-title":"Generative pre-training for speech with autoregressive predictive coding","author":"chung","year":"2020","journal-title":"ICASSP"},{"key":"ref37","article-title":"Self-supervised learning from a multi-view perspective","author":"tsai","year":"2020"},{"key":"ref36","article-title":"Data augmenting contrastive learning of speech representations in the time domain","author":"kharitonov","year":"2020"},{"key":"ref35","article-title":"Audio albert: A lite bert for self-supervised learning of audio representation","author":"chi","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref10","article-title":"Effectiveness of self-supervised pre-training for speech recognition","author":"baevski","year":"2019"},{"key":"ref40","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"NeurIPS"},{"key":"ref11","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020"},{"key":"ref12","article-title":"Utilizing untranscribed training data to improve performance","author":"zavaliagkos","year":"1998","journal-title":"DARPA Broadcast News Transcription and Understanding Workshop"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660839"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"ref15","article-title":"Semi-supervised speech recognition via local prior matching","author":"hsu","year":"2020"},{"key":"ref16","article-title":"Deep clustering for unsupervised learning of visual features","author":"caron","year":"2018","journal-title":"ECCV"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1532"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-3084","article-title":"A convolutional deep markov model for unsupervised speech representation learning","author":"khurana","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1160"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref29","article-title":"An un-supervised autoregressive model for speech representation learning","author":"chung","year":"2019"},{"key":"ref5","article-title":"Representation learning with contrastive predictive coding","author":"den oord","year":"2018"},{"key":"ref8","article-title":"Neural discrete representation learning","author":"den oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/089976602317318938"},{"key":"ref2","article-title":"Electra: Pre-training text encoders as discriminators rather than generators","author":"clark","year":"2020"},{"key":"ref9","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019"},{"key":"ref1","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref20","article-title":"A nonparametric bayesian approach to acoustic model discovery","author":"lee","year":"2012","journal-title":"ACL"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/18.720541"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"ref42","article-title":"wav2letter++: The fastest open-source speech recognition system","author":"pratap","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-349"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1452"},{"key":"ref26","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"2017","journal-title":"NeurIPS"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003972"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414460.pdf?arnumber=9414460","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:32:35Z","timestamp":1672129955000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414460\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414460","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}