{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:14:47Z","timestamp":1759335287271,"version":"3.37.3"},"reference-count":52,"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":"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3087020","type":"journal-article","created":{"date-parts":[[2021,6,14]],"date-time":"2021-06-14T19:58:34Z","timestamp":1623700714000},"page":"2539-2552","source":"Crossref","is-referenced-by-count":10,"title":["Speaker-Independent Speech Animation Using Perceptual Loss Functions and Synthetic Data"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6856-772X","authenticated-orcid":false,"given":"Danny","family":"Websdale","sequence":"first","affiliation":[{"name":"School of Computing Sciences, University of East Anglia, Norwich, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1299-0446","authenticated-orcid":false,"given":"Sarah","family":"Taylor","sequence":"additional","affiliation":[{"name":"School of Computing Sciences, University of East Anglia, Norwich, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8208-4882","authenticated-orcid":false,"given":"Ben","family":"Milner","sequence":"additional","affiliation":[{"name":"School of Computing Sciences, University of East Anglia, Norwich, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-483"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2279659"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2019.00069"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1084"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073699"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.917336"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-4-431-66911-1_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/566570.566594"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/cav.1892"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258880"},{"key":"ref12","first-page":"275","article-title":"Dynamic units of visual speech","volume-title":"Proc. Eurographics\/ACM SIGGRAPH Symp. Comput. Animation","author":"Taylor","year":"2012"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-569"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.434"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178899"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783356"},{"key":"ref17","first-page":"37","article-title":"End-to-end speech-driven realistic facial animation with temporal GANs","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Vougioukas","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3243017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-014-2156-2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"volume-title":"114: Transmission Systems and Media, Digital Systems and Networks, International Telecommunication Union Std","year":"2003","author":"ITU-T","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2066"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67401-8_49"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2014.6890554"},{"article-title":"Visual speech synthesis by learning joint probabilistic models of audio and video","year":"2012","author":"Deena","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2281036"},{"key":"ref27","first-page":"88","article-title":"HMM-based visual speech synthesis using dynamic visemes","volume-title":"Proc. Conf. Facial Analysis, Animation Auditory-Vis. Speech Process.","author":"Thangthai","year":"2015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472730"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.08.011"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953092"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-137"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-47665-0_18"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201292"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2947741"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3243017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2916031"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00009"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/34.927467"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029666.37597.d3"},{"key":"ref45","first-page":"102","article-title":"Comparing visual features for lipreading","volume-title":"Proc. Int. Conf. Auditory-Visual Speech Process.","author":"Lan","year":"2009"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/BF02291478"},{"article-title":"Speech Processing, Transmission and Quality Aspects (STQ); Distributed speech recognition; extended advanced front-end feature extraction algorithm; compression algorithms; back-end speech reconstruction algorithm","volume-title":"ETSI STQ-Aurora DSR Work. Group","year":"2003","key":"ref47"},{"key":"ref48","article-title":"Deep belief networks for phone recognition","volume-title":"NIPS Workshop Deep Learn. Speech Recognit. Related Applicat","author":"Mohamed","year":"2009"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.31390\/gradschool_dissertations.4601"},{"key":"ref50","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proc. ICML","volume":"30","author":"Maas","year":"2013"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947374"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09454300.pdf?arnumber=9454300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T22:59:37Z","timestamp":1705013977000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9454300\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3087020","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2022]]}}}