{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:09:52Z","timestamp":1779379792676,"version":"3.53.1"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"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 J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/jstsp.2022.3188113","type":"journal-article","created":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T20:03:29Z","timestamp":1656965009000},"page":"1505-1518","source":"Crossref","is-referenced-by-count":1605,"title":["WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3082-6052","authenticated-orcid":false,"given":"Sanyuan","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5715-3011","authenticated-orcid":false,"given":"Yu","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Corp., Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1089-9748","authenticated-orcid":false,"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Corp., Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8628-3288","authenticated-orcid":false,"given":"Naoyuki","family":"Kanda","sequence":"additional","affiliation":[{"name":"Microsoft Corp., Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[{"name":"Microsoft Corp., Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Microsoft Corp., Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft Corp., Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Ren","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0314-3790","authenticated-orcid":false,"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Qian","sequence":"additional","affiliation":[{"name":"Microsoft Corp., Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft Corp., Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Zeng","sequence":"additional","affiliation":[{"name":"Microsoft Corp., Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangzhan","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Furu","family":"Wei","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref2","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang","year":"2019"},{"issue":"140","key":"ref3","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref4","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref5","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","first-page":"10937","article-title":"UniSpeech: Unified speech representation learning with labeled and unlabeled data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref10","article-title":"SpeechStew: Simply mix all available speech recognition data to train one large neural network","author":"Chan","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1758"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-236"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.427"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2650"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413423"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687875"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2922832"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-349"},{"key":"ref26","first-page":"1876","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hsu","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.213"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-349"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref39","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baevski","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054224"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746038"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref47","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1609"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-921"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref51","article-title":"CogView: Mastering text-to-image generation via transformers","author":"Ding","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref54","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref56","article-title":"The speakin system for VoxCeleb speaker recognition challange 2021","author":"Zhao","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414600"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947357"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-64"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref61","article-title":"Neural speaker diarization with speaker-wise chain rule","author":"Fujita","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3162080"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1004"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref67","article-title":"2000 NIST speaker recognition evaluation","author":"Przybocki","year":"2001"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1778"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64680-0_7"},{"key":"ref71","article-title":"CSR-II (WSJ1) complete","author":"Philadelphia","year":"1994"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462081"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1121\/1.2799929"},{"key":"ref75","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2018"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413933"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-142"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747144"},{"key":"ref79","article-title":"End-to-end ASR: From supervised to semi-supervised learning with modern architectures","author":"Synnaeve","year":"2019"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref85","article-title":"Reducing transformer depth on demand with structured dropout","author":"Fan","year":"2019"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683535"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9923627\/09814838.pdf?arnumber=9814838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:54:50Z","timestamp":1706763290000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9814838\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":88,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2022.3188113","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}