{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T21:04:04Z","timestamp":1774991044487,"version":"3.50.1"},"reference-count":188,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFB3100800"],"award-info":[{"award-number":["2021YFB3100800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["331883"],"award-info":[{"award-number":["331883"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376283"],"award-info":[{"award-number":["62376283"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872379"],"award-info":[{"award-number":["61872379"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tpami.2024.3376710","type":"journal-article","created":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:11:06Z","timestamp":1710357066000},"page":"6001-6022","source":"Crossref","is-referenced-by-count":38,"title":["Deep Learning for Visual Speech Analysis: A Survey"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6255-754X","authenticated-orcid":false,"given":"Changchong","family":"Sheng","sequence":"first","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2620-889X","authenticated-orcid":false,"given":"Gangyao","family":"Kuang","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7667-6539","authenticated-orcid":false,"given":"Liang","family":"Bai","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology (NUDT), Changsha, Hunan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9335-0469","authenticated-orcid":false,"given":"Chenping","family":"Hou","sequence":"additional","affiliation":[{"name":"College of Liberal Arts and Sciences, National University of Defense Technology (NUDT), Changsha, Hunan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3238-745X","authenticated-orcid":false,"given":"Xin","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2263-6731","authenticated-orcid":false,"given":"Matti","family":"Pietik\u00e4inen","sequence":"additional","affiliation":[{"name":"Center for Machine Vision and Signal Analysis, Oulu University, Oulu, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2011-2873","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, Hunan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/79.911195"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1955"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682863"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8462527"},{"key":"ref8","first-page":"4485","article-title":"Transfer learning from speaker verification to\n                        multispeaker text-to-speech synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jia"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0b013e31812f7185"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.116"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242599"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12552"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817150"},{"key":"ref20","article-title":"Robust speech recognition using articulatory\n                        information","author":"Kirchho","year":"1999"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.1998.999008"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/34.982900"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1891903.1891942"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.434"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783356"},{"key":"ref26","first-page":"1097","article-title":"ImageNet classification with deep convolutional\n                        neural networks","volume-title":"Proc. Int. Conf. Neural\n                        Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178899"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756582"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413623"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01312"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20210"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6174"},{"key":"ref37","first-page":"820","article-title":"Dual learning for machine\n                        translation","volume-title":"Proc. Int. Conf. Neural Inf.\n                        Process. Syst.","author":"He"},{"key":"ref38","first-page":"2672","article-title":"Generative adversarial\n                    nets","volume-title":"Proc. Int. Conf. Neural Inf. Process.\n                        Syst.","author":"Goodfellow"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/129"},{"key":"ref41","article-title":"End-to-end speech-driven facial animation with\n                        temporal GANs","author":"Vougioukas","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref43","article-title":"What comprises a good talking-head video generation?:\n                        A survey and benchmark","author":"Chen","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3107946"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2018.07.002"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.11.001"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.004"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682524"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1113"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475415"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3146"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3102433"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref57","article-title":"LipNet: End-to-end sentence-level\n                        lipreading","author":"Assael","year":"2016"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00510"},{"key":"ref59","article-title":"Multi-grained spatio-temporal modeling for\n                        lip-reading","author":"Wang","year":"2019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1943"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00080"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00088"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682868"},{"key":"ref65","article-title":"ObamaNet: Photo-realistic lip-sync from\n                        text","author":"Kumar","year":"2017"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073699"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00278"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/141"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3142387"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688191"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2004-424"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-016-0438-z"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163155"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178347"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref92","article-title":"LRS3-TED: A large-scale dataset for visual speech\n                        recognition","author":"Afouras","year":"2018"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1669"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2279"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987720"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10861"},{"key":"ref108","article-title":"DeepFakes: A new threat to face recognition?\n                        Assessment and detection","author":"Korshunov","year":"2018"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.34"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-43958-7_40"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/34.682181"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"issue":"2","key":"ref116","article-title":"OpenFace: A general-purpose face recognition\n                        library with mobile applications","volume":"6","author":"Amos","year":"2016","journal-title":"CMU Sch.\n                        Comput. Sci."},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/QOMEX.2009.5246972"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.21437\/AVSP.2017-13"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1883\/1\/012083"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084827"},{"key":"ref124","article-title":"Very deep convolutional networks for large scale\n                        image recognition","volume-title":"Proc. Int. Conf.\n                        Learn. Representations","author":"Simonyan"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref126","article-title":"MobileNets: Efficient convolutional neural\n                        networks for mobile vision applications","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern\n                    Recognit.","author":"Howard"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref129","article-title":"Learn an effective lip reading model without\n                        pains","author":"Feng","year":"2020"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2618"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref133","article-title":"Learning spatio temporal features with two stream\n                        deep 3D CNNs for lipreading","volume-title":"Proc. Brit.\n                        Mach. Vis. Conf.","author":"Weng"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-019-01630-1"},{"key":"ref135","first-page":"802","article-title":"Convolutional LSTM network: A machine learning\n                        approach for precipitation nowcasting","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shi"},{"key":"ref136","first-page":"5998","article-title":"Attention is all you\n                    need","volume-title":"Proc. Int. Conf. Neural Inf. Process.\n                        Syst.","author":"Vaswani"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054127"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747729"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref147","first-page":"7763","article-title":"Cooperative learning of audio and video models from\n                        self-supervised synchronization","volume-title":"Proc.\n                        Int. Conf. Neural Inf. Process. Syst.","author":"Korbar"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1360"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258880"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.537"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.843341"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.888009"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01150-y"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1097-z"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206665"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_25"},{"key":"ref160","article-title":"Deep speech: Scaling up end-to-end speech\n                        recognition","author":"Hannun","year":"2014"},{"key":"ref161","article-title":"Speech-driven facial reenactment using conditional\n                        generative adversarial networks","author":"Jalalifar","year":"2018"},{"key":"ref162","article-title":"Conditional generative adversarial\n                        nets","author":"Mirza","year":"2014"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref164","first-page":"7135","article-title":"First order motion model for image\n                        animation","volume-title":"Proc. Int. Conf. Neural Inf.\n                        Process. Syst.","author":"Siarohin"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480484"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02104"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.287"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3243017"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3353745"},{"key":"ref171","article-title":"Audio-driven talking face video generation with\n                        learning-based personalized head pose","author":"Yi","year":"2020"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1145\/3449063"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00100"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2013.249"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201283"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356500"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146783"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475280"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00384"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16286"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322999"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3107669"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"ref188","article-title":"You said that?","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Chung"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1996"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2916031"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3099900"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351066"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054103"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413844"},{"key":"ref199","article-title":"Talking head generation with audio and speech related\n                        facial action units","volume-title":"Proc. Brit. Mach.\n                        Vis. Conf.","author":"Chen"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/327"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_39"},{"key":"ref203","article-title":"Real-time neural radiance talking portrait\n                        synthesis via audio-spatial decomposition","author":"Tang","year":"2022"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"ref205","article-title":"GeneFace: Generalized and high-fidelity audio-driven\n                        3D talking face synthesis","volume-title":"Proc. Int.\n                        Conf. Learn. Representations","author":"Ye"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10627928\/10472054.pdf?arnumber=10472054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T06:12:21Z","timestamp":1723183941000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10472054\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":188,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3376710","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":[[2024,9]]}}}