{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T15:25:06Z","timestamp":1780327506731,"version":"3.54.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"EPSRC Programme","award":["Seebibyte EP\/M013774\/1"],"award-info":[{"award-number":["Seebibyte EP\/M013774\/1"]}]},{"name":"EPSRC CDT"},{"name":"Oxford-Google DeepMind Graduate Scholarship"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1109\/tpami.2018.2889052","type":"journal-article","created":{"date-parts":[[2018,12,21]],"date-time":"2018-12-21T20:53:16Z","timestamp":1545425596000},"page":"8717-8727","source":"Crossref","is-referenced-by-count":460,"title":["Deep Audio-Visual Speech Recognition"],"prefix":"10.1109","volume":"44","author":[{"given":"Triantafyllos","family":"Afouras","sequence":"first","affiliation":[{"name":"University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7741-7275","authenticated-orcid":false,"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[{"name":"University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Senior","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7848-7283","authenticated-orcid":false,"given":"Oriol","family":"Vinyals","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8945-8573","authenticated-orcid":false,"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[{"name":"University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472088"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-014-0629-7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref32","article-title":"Letter-based speech recognition with gated convnets","author":"liptchinsky","year":"2017","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1142\/S021946780100027X"},{"key":"ref30","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-293"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178347"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1038"},{"key":"ref34","first-page":"674","article-title":"An iterative image registration technique with an application to stereo vision","author":"lucas","year":"1981","journal-title":"Proc 7th Int Joint Conf Artif Intell"},{"key":"ref28","article-title":"ADAM: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref27","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.69"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1943"},{"key":"ref1","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016"},{"key":"ref20","first-page":"2714","article-title":"Audio-visual speech recognition incorporating facial depth information captured by the Kinect","author":"galatas","year":"2012","journal-title":"Proc 20th Eur Signal Process Conf"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref21","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"ICML Workshop on Representation Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472852"},{"key":"ref51","article-title":"Residual convolutional CTC networks for automatic speech recognition","author":"wang","year":"2017"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.004"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1446"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462015"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1121\/1.2935783"},{"key":"ref52","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"CoRR"},{"key":"ref10","article-title":"End-to-end continuous speech recognition using attention-based recurrent NN: First results","author":"chorowski","year":"2014","journal-title":"Proc NIPS Workshop Deep Learn"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref11","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref13","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref14","first-page":"251","article-title":"Out of time: Automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref15","article-title":"Lip reading in profile","author":"chung","year":"2017","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref16","article-title":"Wav2Letter: An end-to-end convnet-based speech recognition system","author":"collobert","year":"2016","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-016-0438-z"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref4","article-title":"LipNet: Sentence-level lipreading","author":"assael","year":"2016"},{"key":"ref3","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"afouras","year":"2018"},{"key":"ref6","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"bai","year":"2018"},{"key":"ref5","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref49","first-page":"5998","article-title":"Attention Is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref7","first-page":"4960","article-title":"Listen, attend and spell","author":"chan","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref46","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2015.7415335"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-350"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref44","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref43","article-title":"Large-scale visual speech recognition","author":"shillingford","year":"2018","journal-title":"arXiv 1807 05162"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9940447\/08585066.pdf?arnumber=8585066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T23:13:08Z","timestamp":1670281988000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8585066\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":56,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2018.2889052","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,1]]}}}