{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T23:40:15Z","timestamp":1714002015082},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2012,10]]},"DOI":"10.1109\/tasl.2012.2202651","type":"journal-article","created":{"date-parts":[[2012,6,5]],"date-time":"2012-06-05T19:20:16Z","timestamp":1338924016000},"page":"2378-2387","source":"Crossref","is-referenced-by-count":9,"title":["Relating Objective and Subjective Performance Measures for AAM-Based Visual Speech Synthesis"],"prefix":"10.1109","volume":"20","author":[{"given":"Barry-John","family":"Theobald","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iain","family":"Matthews","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1155\/2009\/174192"},{"key":"ref72","article-title":"MASSY speaks English: Adaptation and evaluation of a talking head","author":"fagel","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.10.006"},{"key":"ref70","first-page":"139","article-title":"Evaluation of a viseme-driven talking head","author":"dey","year":"2010","journal-title":"Proc Theory and Practice of Computer Graphics Conf"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1155\/2009\/169819"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-643"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21236\/ADA459909"},{"key":"ref74","first-page":"148","article-title":"Optimized photorealistic audiovisual speech synthesis using active appearance modeling","author":"mattheyses","year":"2010","journal-title":"Proc Int Conf Auditory-Vis Speech Process"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-590"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.850964"},{"key":"ref78","author":"theobald","year":"2003","journal-title":"Visual speech synthesis using shape and appearance models"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366215"},{"key":"ref33","first-page":"90","article-title":"Creating and controlling video-realistic talking heads","author":"elisei","year":"2001","journal-title":"Proc Int Conf Auditory Vis Speech Process"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865480"},{"key":"ref31","author":"parke","year":"1996","journal-title":"Computer Facial Animation"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.07.002"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"37","DOI":"10.21437\/Eurospeech.2003-10","article-title":"ISCA special session: Hot topics in speech synthesis","author":"bailly","year":"2003","journal-title":"Proc EUROSPEECH"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/34.927467"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8659.t01-1-00712"},{"key":"ref34","article-title":"Animatable facial reflectance fields","author":"hawkins","year":"2004","journal-title":"Proc Eurograph Symp Rendering"},{"key":"ref60","first-page":"1279","article-title":"Audio-visual synthesis of talking faces from speech production correlates","volume":"3","author":"kuratate","year":"1999","journal-title":"Proc EUROSPEECH"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.5244\/C.23.10"},{"key":"ref61","first-page":"49","article-title":"Acoustic viseme modelling for speech driven animation: A case study","author":"dongmei","year":"2002","journal-title":"Proc Workshop Model-Based Process Coding of Audio"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s003710050182"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745033"},{"key":"ref64","article-title":"Intelligibility of natural and 3D-cloned German speech","author":"fagel","year":"2007","journal-title":"Proc Int Conf Auditory-Vis Speech Process"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-620"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00045-4"},{"key":"ref66","doi-asserted-by":"crossref","first-page":"3657","DOI":"10.1016\/j.sigpro.2006.02.039","article-title":"Design, implementation and evaluation of the czech realistic audio-visual speech synthesis","volume":"86","author":"elezn","year":"2006","journal-title":"Signal Process"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-354"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(96)00026-X"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/1077399.1077405"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-27817-7_173"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1023\/A:1025700715107","article-title":"Audiovisual speech synthesis","volume":"6","author":"bailly","year":"2003","journal-title":"Int J Speech Technol"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-194"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258880"},{"key":"ref21","first-page":"817","article-title":"Real time speech driven facial animation using formant analysis","author":"wen","year":"2001","journal-title":"Proc Int Conf Multimedia Expo"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1049\/cp:20061940"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1891903.1891942"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/566570.566594"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CA.1998.681913"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-590"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2011538"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/WSS.2002.1224365"},{"key":"ref58","first-page":"175","article-title":"3D face point trajectory synthesis using an automatically derived visual phoneme similarity matrix","author":"arslan","year":"1998","journal-title":"Proc Int Conf Auditory-Vis Speech Process"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-498"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.02.015"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1023\/B:IJST.0000037076.86366.8d"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.1998.738912"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.843341"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CGI.1998.694263"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00048-X"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311537"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(02)00161-7"},{"key":"ref13","first-page":"51","article-title":"Speech driven synthesis of talking head sequences","author":"eisert","year":"1997","journal-title":"Proc Workshop 3D Image Anal Synth"},{"key":"ref14","article-title":"A probabilistic model for generating realistic speech movements from speech","author":"englebienne","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","first-page":"15","article-title":"A comparative study of direct and ASR-based modular audio to visual speech systems","volume":"97 98","author":"feldhoffer","year":"2008","journal-title":"The Phonetician"},{"key":"ref82","author":"wakerly","year":"2002","journal-title":"Mathematical Statistics with Applications"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2002.1021892"},{"key":"ref81","first-page":"7","article-title":"On evaluating synthesised visual speech","author":"theobald","year":"2008","journal-title":"Proc Int Conf Auditory Vis Speech Process"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2005.04.002"},{"key":"ref18","article-title":"Picture my voice: Audio to visual speech synthesis using artificial neural networks","author":"massaro","year":"1999","journal-title":"Proc Int Conf Auditory Vis Speech Process"},{"key":"ref19","article-title":"Real-time visual speech synthesis using active appearance models","author":"theobald","year":"2007","journal-title":"Proc Int Conf Auditory Vis Speech Process"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1142\/S0218202501000726"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.1982.1674492"},{"key":"ref3","author":"massaro","year":"1998","journal-title":"Perceiving Talking Faces"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.840611"},{"key":"ref5","first-page":"33","article-title":"Degrees of freedom of facial movements in face-to-face conversational speech","author":"bailly","year":"2006","journal-title":"Proc Int Workshop Multimodal Corpora"},{"key":"ref8","first-page":"27","article-title":"Geometry-based muscle modelling for facial animation","author":"khler","year":"2001","journal-title":"Graphics Interface"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2010213"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0023830909103181"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/218380.218407"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2006.18"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-594"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2005.43"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1002\/cav.32"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.1998.670941"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TDPVT.2002.1024147"},{"key":"ref44","first-page":"665","article-title":"Evaluation of a system for concatenative articulatory visual speech synthesis","author":"engwall","year":"2002","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2006.90"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/10376\/6263279\/06212334.pdf?arnumber=6212334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T23:25:22Z","timestamp":1714001122000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6212334\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,10]]},"references-count":82,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2012.2202651","relation":{},"ISSN":["1558-7916","1558-7924"],"issn-type":[{"value":"1558-7916","type":"print"},{"value":"1558-7924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,10]]}}}