{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:14:16Z","timestamp":1771611256077,"version":"3.50.1"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1741472"],"award-info":[{"award-number":["1741472"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3099900","type":"journal-article","created":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T21:37:58Z","timestamp":1627335478000},"page":"3480-3490","source":"Crossref","is-referenced-by-count":78,"title":["Speech Driven Talking Face Generation From a Single Image and an Emotion Condition"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6259-5925","authenticated-orcid":false,"given":"Sefik Emre","family":"Eskimez","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Cognitive Services Research (CSR) team, Microsoft, Bellevue, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4649-278X","authenticated-orcid":false,"given":"You","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8334-9974","authenticated-orcid":false,"given":"Zhiyao","family":"Duan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.06.011"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2021.3062200"},{"key":"ref33","first-page":"2236","article-title":"Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph","volume":"1","author":"zadeh","year":"0","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.08.003"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.01.095"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CIHLI.2013.6613272"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.10.011"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-021-09824-x"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.4018\/IJSSMET.2019040103"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.04.024"},{"key":"ref60","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervention"},{"key":"ref62","article-title":"Data augmentation with balancing GAN","author":"mariani","year":"2018"},{"key":"ref61","first-page":"5767","article-title":"Improved training of wasserstein gans","author":"gulrajani","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref63","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.9"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhk024"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3390\/info11020125"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55394-8_1"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2019.8906538"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1967.10500917"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.3110132"},{"key":"ref1","first-page":"43","article-title":"Bi-sensory articulation functions for normal hearing and sensorineural hearing loss patients","volume":"6","author":"binnie","year":"1973","journal-title":"J Acad Rehabilitative Audiology"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18564\/jasss.3681"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.2992799"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34584-5_11"},{"key":"ref24","volume":"11","author":"ekman","year":"2013","journal-title":"Emotion in the human face Guidelines for research and an integration of findings"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/0470013494.ch3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref25","author":"mehrabian","year":"1974","journal-title":"An Approach to Environmental Psychology"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865480"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2916031"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2015.00611"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-019-00524-z"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/1027933.1027968"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2009.0139"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2013.00369"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-381"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2017.01.001"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02074-w"},{"key":"ref10","first-page":"1","article-title":"Realistic speech-driven facial animation with gans","author":"vougioukas","year":"2019","journal-title":"Int J Comput Vis"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00089"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2001355"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.917336"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1001\/archpsyc.1963.01720100052006"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472082"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-009-9017-8"},{"key":"ref18","first-page":"137","article-title":"Psychological models of emotion","volume":"137","author":"scherer","year":"2000","journal-title":"The Neuropsychology of Emotion"},{"key":"ref19","first-page":"651","article-title":"Emotion models: A review","volume":"10","author":"ps","year":"2017","journal-title":"J Control Theory Applied"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.04995"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.1836832"},{"key":"ref6","article-title":"You said that","author":"chung","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01150-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93764-9_35"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054103"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/129"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2004908"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.888009"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.837256"},{"key":"ref42","article-title":"End-to-end speech-driven facial animation with temporal GANs","author":"vougioukas","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.840611"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6046\/9687854\/9496264-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09496264.pdf?arnumber=9496264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,5]],"date-time":"2022-08-05T00:33:52Z","timestamp":1659659632000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9496264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3099900","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}