{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:23:17Z","timestamp":1776889397629,"version":"3.51.2"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096387","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["UFO2: A Unified Pre-Training Framework for Online and Offline Speech Recognition"],"prefix":"10.1109","author":[{"given":"Li","family":"Fu","sequence":"first","affiliation":[{"name":"JD AI Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siqi","family":"Li","sequence":"additional","affiliation":[{"name":"JD AI Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingtao","family":"Li","sequence":"additional","affiliation":[{"name":"JD AI Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liping","family":"Deng","sequence":"additional","affiliation":[{"name":"JD AI Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangzhu","family":"Li","sequence":"additional","affiliation":[{"name":"JD AI Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Fan","sequence":"additional","affiliation":[{"name":"JD AI Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Chen","sequence":"additional","affiliation":[{"name":"JD AI Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodong","family":"He","sequence":"additional","affiliation":[{"name":"JD AI Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Wav2vec2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3171967"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053165"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054715"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413692"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687910"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054099"},{"key":"ref16","article-title":"Deploying self- supervised learning in the wild for hybrid automatic speech recognition","author":"Karimi","year":"2022"},{"key":"ref17","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"Proc. ICML","author":"Chiu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-412"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1454"},{"key":"ref20","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NeurIPS","author":"Hinton"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref22","article-title":"Dual-mode asr: Unify and improve streaming asr with full-context modeling","volume-title":"Proc. ICLR","author":"Yu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022446"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref25","article-title":"Pushing the limits of semi- supervised learning for automatic speech recognition","volume-title":"Proc. NeurIPS","author":"Zhang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref27","article-title":"Vq-wav2vec: Self- supervised learning of discrete speech representations","volume-title":"Proc. ICLR","author":"Baevski"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413535"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747706"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3216"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref37","article-title":"Enhancing the ted-lium corpus with selected data for language modeling and more ted talks","volume-title":"Proc. LREC","author":"Rousseau"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096387.pdf?arnumber=10096387","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T05:35:53Z","timestamp":1712900153000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096387\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096387","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}