{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T13:26:13Z","timestamp":1774877173237,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2009,3,1]],"date-time":"2009-03-01T00:00:00Z","timestamp":1235865600000},"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. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2009,3]]},"DOI":"10.1109\/tasl.2008.2008740","type":"journal-article","created":{"date-parts":[[2009,2,13]],"date-time":"2009-02-13T19:36:05Z","timestamp":1234553765000},"page":"411-422","source":"Crossref","is-referenced-by-count":22,"title":["Face Active Appearance Modeling and Speech Acoustic Information to Recover Articulation"],"prefix":"10.1109","volume":"17","author":[{"given":"A.","family":"Katsamanis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"G.","family":"Papandreou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P.","family":"Maragos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/34.765658"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587540"},{"key":"ref33","article-title":"audiovisual speech inversion by switching dynamical modeling governed by a hidden markov process","author":"katsamanis","year":"2008","journal-title":"Proc Eur Signal Process Conf (EUSIPCO)"},{"key":"ref32","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00054"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/78.661332"},{"key":"ref37","first-page":"169","article-title":"asynchronous stream modeling for large vocabulary audio-visual speech recognition","author":"luettin","year":"2001","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref36","year":"1996","journal-title":"Speechreading by Humans and Machines"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/BF01897167"},{"key":"ref34","author":"rabiner","year":"1993","journal-title":"Fundamentals of speech recognition"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S0885-2308(03)00005-6"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.906583"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.09.001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.822636"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/79.911195"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00054-5"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011171430700"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.888009"},{"key":"ref18","first-page":"1174","article-title":"on the relationship between face movements, tongue movements, and speech acoustics","volume":"11","author":"jiang","year":"2002","journal-title":"EURASIP J Appl Signal Process"},{"key":"ref19","first-page":"3205","article-title":"introducing visual cues in acoustic-to-articulatory inversion","author":"engwall","year":"2005","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"2261","DOI":"10.21437\/Eurospeech.2003-632","article-title":"resynthesis of 3d tongue movements from facial data","author":"engwall","year":"2003","journal-title":"Proc Eur Conf Speech Commun Technol"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref27","first-page":"305","article-title":"a multichannel articulatory speech database and its application for automatic speech recognition","author":"wrench","year":"2000","journal-title":"Proc 5th Seminar Speech Production"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00048-X"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.2404622"},{"key":"ref29","author":"mardia","year":"1979","journal-title":"Multivariate Analysis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/89.260356"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/01449290600636702"},{"key":"ref7","author":"schroeter","year":"1992","journal-title":"Advances in Speech Signal Processing"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025700715107"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.1921448"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817150"},{"key":"ref20","first-page":"2238","article-title":"reconstructing tongue movements from audio and video","author":"kjellstrm","year":"2006","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1111\/j.2517-6161.1981.tb01169.x","article-title":"reduced-rank regression and canonical analysis","volume":"43","author":"tso","year":"1981","journal-title":"J R Statist Soc (B)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518090"},{"key":"ref21","first-page":"457","article-title":"audiovisual-to-articulatory speech inversion using hmms","author":"katsamanis","year":"2007","journal-title":"Proc Int Workshop Multimedia Signal Process (MMSP)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1984.1172448"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"ref41","author":"young","year":"2002","journal-title":"The HTK Book (for HTK Version 3 2)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/34.927467"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857572"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref43","first-page":"2469","article-title":"a comparison of acoustic features for articulatory inversion","author":"qin","year":"2007","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref25","first-page":"237","article-title":"acoustic-to-articulatory inversion using dynamical and phonological constraints","author":"dusan","year":"2000","journal-title":"Proc Seminar Speech Production"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/10376\/4782026\/04776419.pdf?arnumber=4776419","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T18:19:03Z","timestamp":1738952343000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4776419\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,3]]},"references-count":45,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2008.2008740","relation":{},"ISSN":["1558-7916"],"issn-type":[{"value":"1558-7916","type":"print"}],"subject":[],"published":{"date-parts":[[2009,3]]}}}