{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:02Z","timestamp":1775229902792,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023214","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"9-14","source":"Crossref","is-referenced-by-count":1,"title":["ASBERT: ASR-Specific Self-Supervised Learning with Self-Training"],"prefix":"10.1109","author":[{"given":"Hyung Yong","family":"Kim","sequence":"first","affiliation":[{"name":"42dot Inc.,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byeong-Yeol","family":"Kim","sequence":"additional","affiliation":[{"name":"42dot Inc.,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seung Woo","family":"Yoo","sequence":"additional","affiliation":[{"name":"42dot Inc.,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youshin","family":"Lim","sequence":"additional","affiliation":[{"name":"42dot Inc.,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunkyu","family":"Lim","sequence":"additional","affiliation":[{"name":"42dot Inc.,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanbin","family":"Lee","sequence":"additional","affiliation":[{"name":"42dot Inc.,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Image bert pre-training with online tok-enizer","volume-title":"Proc. ICLR.","author":"Zhou"},{"key":"ref2","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS.","author":"Baevski"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","article-title":"Bert: Pre-training of deep bidirectional transform-ers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref7","article-title":"data2vec: A general frame-work for self-supervised learning in speech, vision and language","volume-title":"Proc. ICML.","author":"Srinivas"},{"key":"ref8","article-title":"Representation learning with contrastive predictive coding","volume-title":"Proc. NeurIPS.","author":"Oord"},{"key":"ref9","article-title":"Vq-wav2vec: Selfsupervised learning of discrete speech representations","author":"Baevski","year":"2019","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref11","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"Proc. ICML","author":"Chiu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref13","article-title":"Pushing the limits of semi -supervised learning for automatic speech recognition","volume-title":"NeurIPS. SAS. Workshop","author":"Zhang"},{"key":"ref14","article-title":"Understanding the role of self attention for efficient speech recognition","volume-title":"Proc. ICLR.","author":"Shim"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-422"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-936"},{"key":"ref19","article-title":"Librispeech: An asr corpus based on publicdomain au-dio books","volume-title":"Proc. ICASSP.","author":"Panayotov"},{"key":"ref20","first-page":"7669","article-title":"Libri-light: A benchmark for asr with limited or nosupervision","volume-title":"Proc. ICASSP.","author":"Kahn"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"wav2letter++: The fastest open-source speech recognition system","author":"Pratap","year":"2018","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414920"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023214.pdf?arnumber=10023214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:36:59Z","timestamp":1707813419000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023214\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023214","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}