{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T00:13:37Z","timestamp":1648858417030},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,2,1]],"date-time":"2013-02-01T00:00:00Z","timestamp":1359676800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1186\/1687-4722-2013-5","type":"journal-article","created":{"date-parts":[[2013,2,1]],"date-time":"2013-02-01T14:52:06Z","timestamp":1359730326000},"source":"Crossref","is-referenced-by-count":2,"title":["A comprehensive system for facial animation of generic 3D head models driven by speech"],"prefix":"10.1186","volume":"2013","author":[{"given":"Lucas D","family":"Terissi","sequence":"first","affiliation":[]},{"given":"Mauricio","family":"Cerda","sequence":"additional","affiliation":[]},{"given":"Juan C","family":"G\u00f3mez","sequence":"additional","affiliation":[]},{"given":"Nancy","family":"Hitschfeld-Kahler","sequence":"additional","affiliation":[]},{"given":"Bernard","family":"Girau","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,2,1]]},"reference":[{"key":"205_CR1","first-page":"75","volume-title":"Proceedings of the ACM SIGGRAPH Conference on Computer Graphics","author":"F Pighin","year":"1998","unstructured":"Pighin F, Hecker J, Lischinski D, Szerisky R, Salesin D: Synthesizing realistic facial expressions from photographs. In Proceedings of the ACM SIGGRAPH Conference on Computer Graphics. San Antonio, TX; 1998:75-84."},{"issue":"2","key":"205_CR2","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1002\/vis.246","volume":"12","author":"B Choe","year":"2001","unstructured":"Choe B, Lee H, Ko HS: Performance-driven muscle-based facial animation. J. Visual. Comput. Animat 2001, 12(2):67-79.","journal-title":"J. Visual. Comput. Animat"},{"issue":"10","key":"205_CR3","doi-asserted-by":"publisher","first-page":"2932","DOI":"10.1016\/j.sigpro.2005.12.007","volume":"86","author":"A Savrana","year":"2006","unstructured":"Savrana A, Arslana LM, Akarunb L: Speaker-independent 3D face synthesis driven by speech and text. Signal Process 2006, 86(10):2932-2951.","journal-title":"Signal Process"},{"key":"205_CR4","first-page":"13","volume":"28","author":"N Ersotelos","year":"2008","unstructured":"Ersotelos N, Dong F: Building highly realistic facial modeling and animation: a survey. Visual Comput 2008, 28: 13-30.","journal-title":"Visual Comput"},{"key":"205_CR5","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/TMM.2004.840611","volume":"7","author":"R Gutierrez-Osuna","year":"2005","unstructured":"Gutierrez-Osuna R, Kakumanu PK, Esposito A, Garcia O, Bojorquez A, Castillo JL, Rudomin I: Speech-driven facial animation with realistic dynamics. IEEE Trans. Multimedia 2005, 7: 33-42.","journal-title":"IEEE Trans. Multimedia"},{"issue":"6","key":"205_CR6","doi-asserted-by":"publisher","first-page":"1523","DOI":"10.1109\/TVCG.2006.90","volume":"12","author":"Z Deng","year":"2006","unstructured":"Deng Z, Neumann U, Lewis J, Kim TY, Bulut M, Narayanan S: Expressive facial animation synthesis by learning speech coarticulation and expression spaces. IEEE Trans. Visual. Comput. Graph 2006, 12(6):1523-1534.","journal-title":"IEEE Trans. Visual. Comput. Graph"},{"key":"205_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1207\/s15516709cog2001_1","volume":"20","author":"C Pelachaud","year":"1996","unstructured":"Pelachaud C, Badler NI, Steedman M: Generating facial expressions for speech. Cognitive Sci 1996, 20: 1-46.","journal-title":"Cognitive Sci"},{"issue":"1-2","key":"205_CR8","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/S0167-6393(98)00054-5","volume":"26","author":"E Yamamoto","year":"1998","unstructured":"Yamamoto E, Nakamura S, Shikano K: Lip movement synthesis from speech based on Hidden Markov Models. Speech Commun 1998, 26(1-2):105-115.","journal-title":"Speech Commun"},{"issue":"4","key":"205_CR9","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1109\/TNN.2002.1021892","volume":"13","author":"P Hong","year":"2002","unstructured":"Hong P, Wen Z, Huang T: Real-time speech-driven face animation with expressions using neural networks. IEEE Trans. Neural Netws 2002, 13(4):916-927.","journal-title":"IEEE Trans. Neural Netws"},{"key":"205_CR10","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1109\/41.661300","volume":"45","author":"R Rao","year":"1998","unstructured":"Rao R, Chen T, Mersereau R: Audio-to-visual conversion for multimedia communication. IEEE Trans. Indus. Electron 1998, 45: 15-22.","journal-title":"IEEE Trans. Indus. Electron"},{"issue":"2","key":"205_CR11","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1109\/TMM.2005.843341","volume":"7","author":"S Fu","year":"2005","unstructured":"Fu S, Gutierrez-Osuna R, Esposito A, Kakumanu P, Garcia O: Audio\/visual mapping with cross-modal Hidden Markov Models. IEEE Trans. Multimedia 2005, 7(2):243-252.","journal-title":"IEEE Trans. Multimedia"},{"issue":"3","key":"205_CR12","doi-asserted-by":"publisher","first-page":"1082","DOI":"10.1109\/TSA.2005.857572","volume":"14","author":"T Hazen","year":"2006","unstructured":"Hazen T: Visual model structures and synchrony constraints for audio-visual speech recognition. IEEE Trans. Audio Speech Lang. Process 2006, 14(3):1082-1089.","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"205_CR13","doi-asserted-by":"publisher","first-page":"1178","DOI":"10.1007\/978-3-540-27817-7_173","volume":"3118","author":"J Beskow","year":"2004","unstructured":"Beskow J, Karlsson I, Kewley J, Salvi G: SynFace: a talking head telephone for the hearing-impaired. Computers helping people with special needs, Lecture Notes in Computer Science 2004, 3118: 1178-1186.","journal-title":"Computers helping people with special needs, Lecture Notes in Computer Science"},{"key":"205_CR14","unstructured":"SynFace Project \n http:\/\/www.speech.kth.se\/synface[LastvisitedonNovember2012]\n \n [Last visited on November 2012]"},{"issue":"1-2","key":"205_CR15","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1023\/A:1011171430700","volume":"29","author":"K Choi","year":"2001","unstructured":"Choi K, Luo Y, Hwang J: Hidden Markov model inversion for audio-to-visual conversion in an MPEG-4 facial animation system. J. VLSI Signal Process 2001, 29(1-2):51-61.","journal-title":"J. VLSI Signal Process"},{"issue":"3","key":"205_CR16","doi-asserted-by":"publisher","first-page":"631","DOI":"10.1111\/1467-8659.t01-2-00711","volume":"22","author":"S Kshirsagar","year":"2003","unstructured":"Kshirsagar S, Magnenat-Thalmann N: Visyllable based speech animation. Comput. Graph. Forum 2003, 22(3):631-639.","journal-title":"Comput. Graph. Forum"},{"issue":"6","key":"205_CR17","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1016\/j.specom.2005.09.005","volume":"48","author":"P Kakumanu","year":"2006","unstructured":"Kakumanu P, Esposito A, Garcia ON, Gutierrez-Osuna R: A comparison of acoustic coding models for speech-driven facial animation. Speech Commun 2006, 48(6):598-615.","journal-title":"Speech Commun"},{"issue":"3","key":"205_CR18","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1109\/TASL.2008.2011538","volume":"17","author":"J Tao","year":"2009","unstructured":"Tao J, Xin L, Yin P: Realistic visual speech synthesis based on hybrid concatenation method. IEEE Trans. Audio Speech Lang. Process 2009, 17(3):469-477.","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"205_CR19","volume-title":". EURASIP J. Adv. Signal Process","author":"J Tao","year":"2011","unstructured":"Tao J, Pan S, Yang M, Li Y, Mu K, Che J: Utterance independent bimodal emotion recognition in spontaneous communication. EURASIP J. Adv. Signal Process 2011., 4(4):"},{"issue":"3-4","key":"205_CR20","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1002\/cav.80","volume":"16","author":"C Busso","year":"2005","unstructured":"Busso C, Deng Z, Neumann U, Narayanan SS: Natural head motion synthesis driven by acoustic prosodic features. J. Comput. Animat. Virtual Worlds 2005, 16(3-4):283-290.","journal-title":"J. Comput. Animat. Virtual Worlds"},{"issue":"3","key":"205_CR21","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.1109\/TASL.2006.885910","volume":"15","author":"C Busso","year":"2007","unstructured":"Busso C, Deng Z, Grimm M, Neumann U, Narayanan S: Rigid head motion in expressive speech animation: analysis and synthesis. IEEE Trans. Audio Speech Lang. Process 2007, 15(3):1075-1086.","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"205_CR22","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-642-10331-5_9","volume":"5875","author":"S Deena","year":"2009","unstructured":"Deena S, Galata A: Speech-driven facial animation using a shared gaussian process latent variable model. Adv. Visual Comput. Lecture Notes in Computer Science 2009, 5875: 89-100.","journal-title":"Adv. Visual Comput. Lecture Notes in Computer Science"},{"issue":"6","key":"205_CR23","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1109\/34.927467","volume":"23","author":"T Cootes","year":"2001","unstructured":"Cootes T, Edwards G, Taylor C: Active appearance models. IEEE Trans. Pattern Anal. Mach. Intell 2001, 23(6):681-685.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"205_CR24","first-page":"133","volume-title":"Proceedings of International Conference on Auditory-Visual Speech Processing","author":"DW Massaro","year":"1999","unstructured":"Massaro DW, Beskow J, Cohen MM, Fry CL, Rodriguez T: Picture my voice: audio to visual speech synthesis using artificial neural networks. In Proceedings of International Conference on Auditory-Visual Speech Processing. Santa Cruz, CA; 1999:133-138."},{"key":"205_CR25","volume-title":"Perceiving Talking Faces: From Speech Perception to a Behavioral Principle","author":"DW Massaro","year":"1998","unstructured":"Massaro DW: Perceiving Talking Faces: From Speech Perception to a Behavioral Principle. MIT Press, Cambridge; 1998."},{"key":"205_CR26","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1109\/79.911195","volume":"18","author":"T Chen","year":"2001","unstructured":"Chen T: Audiovisual speech processing. IEEE Signal Process. Mag 2001, 18: 9-21.","journal-title":"IEEE Signal Process. Mag"},{"key":"205_CR27","first-page":"21","volume-title":"Proceedings of the ACM SIGGRAPH Conference on Computer Graphics","author":"M Brand","year":"1999","unstructured":"Brand M: Voice puppetry. In Proceedings of the ACM SIGGRAPH Conference on Computer Graphics. Los Angeles, CA, USA; 1999:21-28."},{"key":"205_CR28","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1109\/TIT.1967.1054010","volume":"13","author":"AJ Viterbi","year":"1967","unstructured":"Viterbi AJ: Error bounds for convolutional codes and an asymptotically optimal decoding algorithm. IEEE Trans. Inf. Theor 1967, 13: 260-269.","journal-title":"IEEE Trans. Inf. Theor"},{"key":"205_CR29","doi-asserted-by":"publisher","first-page":"2325","DOI":"10.1016\/j.patcog.2006.12.001","volume":"40","author":"L Xie","year":"2007","unstructured":"Xie L, Liu ZQ: A coupled HMM approach to video-realistic speech animation. Pattern Recogn 2007, 40: 2325-2340.","journal-title":"Pattern Recogn"},{"key":"205_CR30","first-page":"145","volume-title":"Proceedings of IEEE International Conf. Acoust., Speech, Signal Processing","author":"S Moon","year":"1995","unstructured":"Moon S, Hwang J: Noisy speech recognition using robust inversion of hidden Markov models. In Proceedings of IEEE International Conf. Acoust., Speech, Signal Processing. Seattle, WA; 1995:145-148."},{"issue":"6","key":"205_CR31","doi-asserted-by":"publisher","first-page":"1783","DOI":"10.1109\/TSP.2004.827153","volume":"52","author":"KH Choi","year":"2004","unstructured":"Choi KH, Hwang JN: Constrained optimization for audio-to-visual conversion. Trans. Signal Process 2004, 52(6):1783-1790.","journal-title":"Trans. Signal Process"},{"issue":"1\u20132","key":"205_CR32","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.specom.2005.02.015","volume":"47","author":"R Carlson","year":"2005","unstructured":"Carlson R, Granstr\u00f6m B: Data-driven multimodal synthesis. Speech Commun 2005, 47(1\u20132):182-193.","journal-title":"Speech Commun"},{"key":"205_CR33","first-page":"1","volume-title":"EURASIP Journal on Audio, Speech and Music Processing","author":"S Ouni","year":"2007","unstructured":"Ouni S, Cohen MM, Ishak H, Massaro DW: Visual contribution to speech perception: measuring the intelligibility of animated talking heads. EURASIP Journal on Audio, Speech and Music Processing 2007, 1-12."},{"key":"205_CR34","first-page":"1","volume-title":"Proceeding of the IEEE International Conference on Multimedia and Expo (ICME)","author":"LD Terissi","year":"2011","unstructured":"Terissi LD, Cerda M, Gomez JC, Hitschfeld-Kahler N, Girau B, Valenzuela R: Animation of generic 3D head models driven by speech. In Proceeding of the IEEE International Conference on Multimedia and Expo (ICME). Barcelona, Spain; 2011:1-6."},{"key":"205_CR35","volume-title":"Fundamentals of Speech Recognition","author":"L Rabiner","year":"1993","unstructured":"Rabiner L, Juang BH Signal Processing Series. In Fundamentals of Speech Recognition. Prentice Hall, New Jersey; 1993."},{"key":"205_CR36","volume-title":"An updated parameterized face","author":"J Ahlberg","year":"2001","unstructured":"Ahlberg J: An updated parameterized face. Technical Report LiTH-ISY-R-2326, Department of Electrical Engineering, Link\u00f6ping University, Sweden (2001)"},{"issue":"6","key":"205_CR37","first-page":"903","volume":"16","author":"LD Terissi","year":"2010","unstructured":"Terissi LD, G\u00f3mez JC: 3D Head Pose and Facial Expression Tracking using a Single Camera. J. Univ. Comput. Sci 2010, 16(6):903-920.","journal-title":"J. Univ. Comput. Sci"},{"key":"205_CR38","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1214\/aoms\/1177697196","volume":"41","author":"LE Baum","year":"1970","unstructured":"Baum LE, Petrie T, Soules G, Weiss N: A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. Annals Math. Stat 1970, 41: 164-171.","journal-title":"Annals Math. Stat"},{"key":"205_CR39","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1145\/1088463.1088500","volume-title":"Proceedings of the Seventh International Conference on Multimodal Interfaces","author":"K Balci","year":"2005","unstructured":"Balci K: XfacEd: authoring tool for embodied conversational agents. In Proceedings of the Seventh International Conference on Multimodal Interfaces. ICMI; 2005:208-213."},{"key":"205_CR40","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/978-0-306-47002-8_3","volume-title":"Proceedings of the Workshop on Deformable Avatars","author":"S Kshirsagar","year":"2001","unstructured":"Kshirsagar S, Garchery S, Magnenat-Thalmann N: Feature point based mesh deformation applied to MPEG-4 facial animation. In Proceedings of the Workshop on Deformable Avatars. Deventer, The Netherlands; 2001:24-34."},{"key":"205_CR41","first-page":"135","volume-title":"Proceedings of Vision, Video, and Graphics","author":"M Sanchez Lorenzo","year":"2003","unstructured":"Sanchez Lorenzo M, Edge JD, King SA, Maddock S: Use and re-use of facial motion capture data. In Proceedings of Vision, Video, and Graphics. Edited by: Hall P, Willis P. Bath, UK; 2003:135-142."},{"key":"205_CR42","first-page":"35","volume-title":"In Short papers proceedings of Eurographics","author":"N Kojekine","year":"2002","unstructured":"Kojekine N, Savchenko V, Senin M, Hagiwara I: Real-time 3D deformations by means of compactly supported radial basis functions. In In Short papers proceedings of Eurographics. Saarbruecken, Germany; 2002:35-43."},{"key":"205_CR43","first-page":"35","volume-title":"Graphics Interface","author":"K Singh","year":"2000","unstructured":"Singh K, Kokkevis E: Skinning characters using surface-oriented free-form deformations. Graphics Interface 2000, 35-42."},{"issue":"5","key":"205_CR44","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1109\/TCSVT.2004.826760","volume":"14","author":"P Aleksic","year":"2004","unstructured":"Aleksic P, Katsaggelos A: Speech-to-video synthesis using MPEG-4 compliant visual features. IEEE Trans. Circ. Systs. Video Technol 2004, 14(5):682-692.","journal-title":"IEEE Trans. Circ. Systs. Video Technol"},{"issue":"4","key":"205_CR45","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1049\/ip-vis:20040752","volume":"151","author":"D Cosker","year":"2004","unstructured":"Cosker D, Marshall A, Rosin P, Hicks Y: Speech-driven facial animation using a hierarchical model. IEE Proc. Vision Image Signal Process 2004, 151(4):314-321.","journal-title":"IEE Proc. Vision Image Signal Process"},{"key":"205_CR46","volume-title":"Nonparametric Statistical Inference","author":"JD Gibbons","year":"2003","unstructured":"Gibbons JD, Chakraborti S: Nonparametric Statistical Inference. Marcel Dekker, Inc., New York; 2003."},{"key":"205_CR47","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1109\/ICMI.2002.1167046","volume-title":"Proceeding of the IEEE Fourth International Conference on Multimodal Interfaces","author":"M Cohen","year":"2002","unstructured":"Cohen M, Massaro D, Clark R: Training a talking head. In Proceeding of the IEEE Fourth International Conference on Multimodal Interfaces. Pittsburgh, PA; 2002:499-510."},{"issue":"2","key":"205_CR48","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L Rabiner","year":"1989","unstructured":"Rabiner L: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 1989, 77(2):257-286.","journal-title":"Proc. IEEE"}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1687-4722-2013-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2013-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2013-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,21]],"date-time":"2019-01-21T21:00:18Z","timestamp":1548104418000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/1687-4722-2013-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,2,1]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,12]]}},"alternative-id":["205"],"URL":"https:\/\/doi.org\/10.1186\/1687-4722-2013-5","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,2,1]]},"article-number":"5"}}