{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T17:41:29Z","timestamp":1769535689901,"version":"3.49.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389778","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:40Z","timestamp":1705671520000},"page":"1-7","source":"Crossref","is-referenced-by-count":5,"title":["Fast-Hubert: an Efficient Training Framework for Self-Supervised Speech Representation Learning"],"prefix":"10.1109","author":[{"given":"Guanrou","family":"Yang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering"}]},{"given":"Ziyang","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering"}]},{"given":"Zhisheng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering"}]},{"given":"Yakun","family":"Song","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering"}]},{"given":"Zhikang","family":"Niu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering"}]},{"given":"Xie","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref2","first-page":"12449","article-title":"Wav2vec 2.0: A framework for selfsupervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Proc. NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-822"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1390"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096308"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref10","article-title":"Leveraging Speech PTM, Text LLM, and Emotional TTS for Speech Emotion Recognition","author":"Ma","year":"2023","journal-title":"arXiv preprint arXiv:2309.10294"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-630"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP43922.2022.9747022","article-title":"Self-supervised learning for speech recognition with intermediate layer supervision","volume-title":"Proc. ICASSP","author":"Wang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-981"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-936"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094922"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10023187"},{"key":"ref17","first-page":"27826","article-title":"Unsupervised speech recognition","volume":"34","author":"Baevski","year":"2021","journal-title":"Proc. NeurIPS"},{"key":"ref18","article-title":"MelHu-BERT: A simplified HuBERT on mel spectrogram","volume-title":"Proc. ICASSP","author":"Lin"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref20","first-page":"1416","article-title":"Efficient self-supervised learning with contextualized target representations for vision, speech and language","volume-title":"Proc. ICML. PMLR","author":"Baevski"},{"key":"ref21","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. ICML","author":"Baevski"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref23","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Proc. NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"issue":"2","key":"ref25","first-page":"23","article-title":"A new algorithm for data compression","volume":"12","author":"Gage","year":"1994","journal-title":"C Users Journal"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389778.pdf?arnumber=10389778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T04:32:08Z","timestamp":1769488328000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389778\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389778","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}