{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:11:37Z","timestamp":1761894697721,"version":"build-2065373602"},"reference-count":30,"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\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","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\/icme59968.2025.11210211","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":["Align-AV-HuBERT: AV-HuBERT with Audio-Visual Temporal Alignment"],"prefix":"10.1109","author":[{"given":"Cancan","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University,Wuhan,China,430072"}]},{"given":"Fei","family":"Su","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University,Wuhan,China,430072"}]},{"given":"Juan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Wuhan University,Wuhan,China,430072"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref3","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","year":"2022","author":"Shi","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10861"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681386"},{"article-title":"Av-lip-sync+: Leveraging av-hubert to exploit multimodal inconsistency for video deepfake detection","year":"2023","author":"Shahzad","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn60899.2024.10650095"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-022-00245-6"},{"key":"ref13","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10625827"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888656"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383616"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/math11122665"},{"article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","year":"2018","author":"Afouras","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"article-title":"Jointly learning visual and auditory speech representations from raw data","year":"2022","author":"Haliassos","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-432"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01312"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref27"},{"article-title":"Electra: Pre-training text encoders as discriminators rather than generators","year":"2020","author":"Clark","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"key":"ref30","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"}],"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\/11210211.pdf?arnumber=11210211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:33:59Z","timestamp":1761888839000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210211\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210211","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}