{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T11:09:53Z","timestamp":1782385793125,"version":"3.54.5"},"reference-count":46,"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\/asru57964.2023.10389642","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":26,"title":["Av-Data2Vec: Self-Supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations"],"prefix":"10.1109","author":[{"given":"Jiachen","family":"Lian","sequence":"first","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexei","family":"Baevski","sequence":"additional","affiliation":[{"name":"Character.AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Ning","family":"Hsu","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Auli","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.55.090902.142028"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0960-88"},{"key":"ref3","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Shi"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10920"},{"key":"ref6","article-title":"Jointly learning visual and auditory speech representations from raw data","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Haliassos"},{"key":"ref7","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"International Conference on Machine Learning(ICML)","author":"Baevski"},{"key":"ref8","article-title":"The use of auditory and visual information during phonetic processing: implications for theories of speech perception. campbell r, dodd b, burnham d, editors. hearing by eye ii: advances in the psychology of speechreading and auditory\u2013 visual speech","author":"Green","year":"1998"},{"key":"ref9","article-title":"u-hubert: Unified mixedmodal speech pretraining and zero-shot transfer to unlabeled modality","author":"Hsu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","article-title":"Neural discrete representation learning","volume":"30","author":"Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-905"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-349"},{"key":"ref16","article-title":"Effectiveness of self-supervised pre-training for speech recognition","author":"Baevski","year":"2019","journal-title":"arXiv preprint arXiv:1911.03912"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref19","first-page":"1416","article-title":"Efficient self-supervised learning with contextualized target representations for vision, speech and language","volume-title":"International Conference on Machine Learning","author":"Baevski"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1669"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00510"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688191"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3275873"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1080\/17512786.2015.1058180"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref33","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref35","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv preprint arXiv:1809.00496"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref37","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"King","year":"2009","journal-title":"The Journal of Machine Learning Research"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1007"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11233"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096401"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096796"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2316"}],"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\/10389642.pdf?arnumber=10389642","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:42:25Z","timestamp":1706028145000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389642\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389642","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}