{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:55:29Z","timestamp":1784303729083,"version":"3.55.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3122291","type":"journal-article","created":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T20:52:27Z","timestamp":1635281547000},"page":"3451-3460","source":"Crossref","is-referenced-by-count":2541,"title":["HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5546-5217","authenticated-orcid":false,"given":"Wei-Ning","family":"Hsu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Bolte","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao-Hung Hubert","family":"Tsai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kushal","family":"Lakhotia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruslan","family":"Salakhutdinov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdelrahman","family":"Mohamed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","volume":"247","author":"bourlard","year":"2012","journal-title":"Connectionist Speech Recognition A Hybrid Approach"},{"key":"ref38","article-title":"Discriminative training for large vocabulary speech recognition","author":"povey","year":"2005"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683131"},{"key":"ref32","first-page":"2041","article-title":"Unsupervised speech representation learning using wavenet autoencoders","volume":"27","author":"chorowski","year":"2019","journal-title":"IEEE Transactions on Audio"},{"key":"ref31","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","volume":"33","author":"hsu","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-349"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/79.536824"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3084"},{"key":"ref60","article-title":"wav2letter : The fastest open-source speech recognition system","author":"pratap","year":"2018"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.033"},{"key":"ref64","article-title":"Self-training and pre-training are complementary for speech recognition","author":"xu","year":"2020"},{"key":"ref27","first-page":"40","article-title":"A nonparametric bayesian approach to acoustic model discovery","author":"lee","year":"0","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003972"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1160"},{"key":"ref2","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"key":"ref20","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref21","article-title":"ELECTRA: Pre-training text encoders as discriminators rather than generators","author":"clark","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref50","article-title":"Audio albert: A lite bert for self-supervised learning of audio representation","author":"chi","year":"2020"},{"key":"ref51","article-title":"Decoar 2.0: Deep contextualized acoustic representations with vector quantization","author":"ling","year":"2020"},{"key":"ref59","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref57","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref55","article-title":"slimipl: Language-model-free iterative pseudo-labeling","author":"likhomanenko","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref53","article-title":"Self-supervised learning from a multi-view perspective","author":"tsai","year":"2020"},{"key":"ref52","article-title":"Effectiveness of self-supervised pre-training for speech recognition","author":"baevski","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"ref11","article-title":"Semi-supervised speech recognition via local prior matching","author":"hsu","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/18.720541"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414079"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1800"},{"key":"ref14","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"caron","year":"2020"},{"key":"ref15","article-title":"Exploring simple siamese representation learning","author":"chen","year":"2020"},{"key":"ref16","article-title":"Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning","author":"grill","year":"2020"},{"key":"ref17","article-title":"Language models are few-shot learners","author":"brown","year":"2020"},{"key":"ref18","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"2019"},{"key":"ref19","article-title":"BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"lewis","year":"2019"},{"key":"ref4","article-title":"Data augmenting contrastive learning of speech representations in the time domain","author":"kharitonov","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref6","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref8","first-page":"301","article-title":"Utilizing untranscribed training data to improve performance","author":"zavaliagkos","year":"0","journal-title":"Proc DARPA Broadcast News Trans Understanding Workshop"},{"key":"ref7","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660839"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.213"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053541"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref41","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"zhang","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2148"},{"key":"ref43","article-title":"Neural discrete representation learning","volume":"33","author":"oord","year":"2017","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09585401.pdf?arnumber=9585401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:02Z","timestamp":1652194442000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9585401\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3122291","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}