{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T10:29:19Z","timestamp":1769509759114,"version":"3.49.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2002,7,1]],"date-time":"2002-07-01T00:00:00Z","timestamp":1025481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw."],"published-print":{"date-parts":[[2002,7]]},"DOI":"10.1109\/tnn.2002.1021892","type":"journal-article","created":{"date-parts":[[2002,11,7]],"date-time":"2002-11-07T19:41:04Z","timestamp":1036698064000},"page":"916-927","source":"Crossref","is-referenced-by-count":69,"title":["Real-time speech-driven face animation with expressions using neural networks"],"prefix":"10.1109","volume":"13","author":[{"family":"Pengyu Hong","sequence":"first","affiliation":[]},{"family":"Zhen Wen","sequence":"additional","affiliation":[]},{"given":"T.S.","family":"Huang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1142\/S0219467801000037"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/192161.192272"},{"key":"ref3","volume-title":"Ananova Limited"},{"key":"ref4","volume-title":"Haptek Corporate"},{"key":"ref5","volume-title":"Inc. LifeFX"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/981732.981747"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511569937.006"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.4324\/9781315799742"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s003710050182"},{"key":"ref10","first-page":"259","article-title":"Model-based image coding","volume-title":"Proc. IEEE","volume":"83","author":"Aizawa"},{"key":"ref11","article-title":"Networked intelligent collaborative environment (netice)","volume-title":"IEEE Int. Conf. Multimedia Expo","author":"Leung"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/500141.500222"},{"key":"ref13","article-title":"Real-time talking head driven by voice and its application to communication and entertainment","volume-title":"Proc. Int. Conf. Auditory-Visual Speech Processing","author":"Morishima"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.1999.817059"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/0470841761"},{"key":"ref16","first-page":"1808","article-title":"Adding the affective dimension: A new look in speech analysis and synthesis","volume-title":"Proc. Int. Conf. Spoken Language Processing 1996","author":"Petrushin"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.608022"},{"key":"ref18","first-page":"141","article-title":"How well can people and computers recognize emotions in speech?","volume-title":"Proc. 1998 AAAI Fall Symp.","author":"Petrushin"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2000-791"},{"key":"ref20","first-page":"3474","article-title":"Recognition of facial expression from optical flow","volume":"E74","author":"Mase","year":"1991","journal-title":"ICICE Trans."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1995.466919"},{"key":"ref22","first-page":"371","article-title":"Tracking and recognizing rigid and nonrigid facial motions using local parametric models of image motion","volume-title":"Proc. Int. Conf. Comput. Vision","author":"Black"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/34.506414"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/34.598232"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311537"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/500141.500196"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF01914862"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/38.180119"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/97880.97906"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/280814.280825"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8659.1130059"},{"key":"ref32","volume-title":"A Parametric Model of Human Faces","author":"Parke","year":"1974"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.1982.1674492"},{"key":"ref34","article-title":"Speech and expression: A computer solution to face animation","volume-title":"Graphics Interface","author":"Pearce","year":"1986"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/37402.37405"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-4-431-66890-9_5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/218380.218407"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/34.216724"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1995.1004"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008122917811"},{"key":"ref41","first-page":"837","article-title":"Audio-visual integration in multimodal communications","volume-title":"Proc. IEEE (Special Issue on Multimedia Signal Processing)","volume":"86","author":"Chen"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.1998.738959"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266799"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00048-X"},{"key":"ref45","article-title":"Exploiting audio\u2013visual correlation in coding of talking head sequences","volume":"45","author":"Rao","year":"1998","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/49.81953"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2000.871547"},{"key":"ref48","article-title":"Picture my voice: Audio to visual speech synthesis using artificial neural networks","volume-title":"Proc. AVSP\u201999","author":"Massaro"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/86.372898"},{"key":"ref50","article-title":"Lip movements synthesis using time-delay","volume-title":"Proc. EUSIPCO-96","author":"Curinga"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1037\/t27734-000"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1999.787002"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-1904-8"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1994.389567"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0054760"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.1998.738971"},{"key":"ref57","volume-title":"Three-Dimensional Computer Vision: A Geometric Viewpoint","author":"Faugeras","year":"1993"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.1994.323794"},{"key":"ref59","volume-title":"Fundamentals of Speech Recognition","author":"Rabiner","year":"1993"},{"key":"ref60","volume-title":"Human Facial Expession: An Evloutionary View","author":"Fridlund","year":"1994"}],"container-title":["IEEE Transactions on Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/72\/21990\/01021892.pdf?arnumber=1021892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T09:32:16Z","timestamp":1742722336000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1021892\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002,7]]},"references-count":60,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2002,7]]}},"URL":"https:\/\/doi.org\/10.1109\/tnn.2002.1021892","relation":{},"ISSN":["1045-9227"],"issn-type":[{"value":"1045-9227","type":"print"}],"subject":[],"published":{"date-parts":[[2002,7]]}}}