{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T02:30:48Z","timestamp":1775010648550,"version":"3.50.1"},"reference-count":33,"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\/icassp49357.2023.10094585","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Learning Cross-Lingual Visual Speech Representations"],"prefix":"10.1109","author":[{"given":"Andreas","family":"Zinonos","sequence":"first","affiliation":[{"name":"Imperial College London,Department of Computing,UK"}]},{"given":"Alexandros","family":"Haliassos","sequence":"additional","affiliation":[{"name":"Imperial College London,Department of Computing,UK"}]},{"given":"Pingchuan","family":"Ma","sequence":"additional","affiliation":[{"name":"Imperial College London,Department of Computing,UK"}]},{"given":"Stavros","family":"Petridis","sequence":"additional","affiliation":[{"name":"Imperial College London,Department of Computing,UK"}]},{"given":"Maja","family":"Pantic","sequence":"additional","affiliation":[{"name":"Imperial College London,Department of Computing,UK"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461886"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414291"},{"key":"ref15","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"shi","year":"2022","journal-title":"Proc ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1360"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref33","article-title":"ELECTRA: pre-training text encoders as discriminators rather than generators","author":"clark","year":"2020","journal-title":"Proc ICLR"},{"key":"ref10","article-title":"Effectiveness of self-supervised pre-training for speech recognition","volume":"abs 1911 3912","author":"baevski","year":"2019","journal-title":"CoRR"},{"key":"ref32","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"ICLR 2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639348"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495646"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref16","author":"haliassos","year":"2022","journal-title":"Jointly learning visual and auditory speech representations from raw data"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383459"},{"key":"ref26","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref20","first-page":"6447","article-title":"Lip reading sentences in the wild","author":"son chung","year":"2017","journal-title":"Proc CVPR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3338533.3366579"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-11"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref8","first-page":"4171","article-title":"BERT: pretraining of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref7","article-title":"Bootstrap your own latent - A new approach to self-supervised learning","author":"grill","year":"2020","journal-title":"Proc NIPS"},{"key":"ref9","article-title":"Vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2020","journal-title":"Proc ICLR"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1038\/s42256-022-00550-z","article-title":"Visual Speech Recognition for Multiple Languages in the Wild","author":"ma","year":"2022","journal-title":"Nature Mach Intell"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01453"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"}],"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\/10094585.pdf?arnumber=10094585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T13:59:41Z","timestamp":1699883981000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094585\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094585","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}