{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:12:33Z","timestamp":1761894753309,"version":"build-2065373602"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209883","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["k2SSL: A Faster and Better Framework for Self-Supervised Speech Representation Learning"],"prefix":"10.1109","author":[{"given":"Yifan","family":"Yang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"}]},{"given":"Jianheng","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"}]},{"given":"Zengrui","family":"Jin","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,China"}]},{"given":"Ziyang","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"}]},{"given":"Xiaoyu","family":"Yang","sequence":"additional","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}]},{"given":"Zengwei","family":"Yao","sequence":"additional","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}]},{"given":"Liyong","family":"Guo","sequence":"additional","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}]},{"given":"Wei","family":"Kang","sequence":"additional","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}]},{"given":"Fangjun","family":"Kuang","sequence":"additional","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}]},{"given":"Long","family":"Lin","sequence":"additional","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}]},{"given":"Daniel","family":"Povey","sequence":"additional","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}]},{"given":"Xie","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. ICML","author":"Baevski","key":"ref5"},{"article-title":"Efficient self-supervised learning with contextualized target representations for vision, speech and language","volume-title":"Proc. ICML","author":"Baevski","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"article-title":"BASE TTS: Lessons from building a billion-parameter text-to-speech model on 100k hours of data","year":"2024","author":"\u0141ajszczak","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"article-title":"Scaling speech technology to 1,000+ languages","year":"2023","author":"Pratap","key":"ref13"},{"article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford","key":"ref14"},{"article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","year":"2023","author":"Zhang","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447120"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.135"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"article-title":"The S3PRL toolkit: Self-supervised speech pre-training and representation learning","year":"2020","author":"Liu","key":"ref21"},{"article-title":"Zipformer: A faster and better encoder for automatic speech recognition","volume-title":"Proc. ICLR","author":"Yao","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1176"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389700"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389778"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-981"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447751"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094922"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-936"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-630"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10023187"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10340"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"article-title":"Lhotse: a speech data representation library for the modern deep learning ecosystem","volume-title":"NeurIPS Data-Centric AI Workshop","author":"\u017belasko","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094567"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683535"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","volume-title":"Proc. NeurIPS Self-Supervised Learning for Speech and Audio Processing Workshop","author":"Zhang","key":"ref43"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209883.pdf?arnumber=11209883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:34:59Z","timestamp":1761888899000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209883\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209883","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}