{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:17:17Z","timestamp":1777569437310,"version":"3.51.4"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2000,6,1]],"date-time":"2000-06-01T00:00:00Z","timestamp":959817600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2000,6,1]],"date-time":"2000-06-01T00:00:00Z","timestamp":959817600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["International Journal of Computer Vision"],"published-print":{"date-parts":[[2000,6]]},"DOI":"10.1023\/a:1008166717597","type":"journal-article","created":{"date-parts":[[2002,12,22]],"date-time":"2002-12-22T08:17:47Z","timestamp":1040545067000},"page":"45-57","source":"Crossref","is-referenced-by-count":68,"title":["Visual Speech Synthesis by Morphing Visemes"],"prefix":"10.1007","volume":"38","author":[{"given":"Tony","family":"Ezzat","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomaso","family":"Poggio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"266550_CR1","doi-asserted-by":"crossref","unstructured":"Avidan, S., Evgeniou, T., Shashua, A., and Poggio, T. 1997. Image-based view synthesis by combining trilinear tensors and learning techniques. In VRST' 97 Proceedings, Lausanne, Switzerland, pp. 103\u2013109.","DOI":"10.1145\/261135.261155"},{"issue":"1","key":"266550_CR2","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/BF01420984","volume":"12","author":"J.L. Barron","year":"1994","unstructured":"Barron, J.L., Fleet, D.J., and Beauchemin, S.S. 1994. Performance of optical flowtechniques. International Journal of Computer Vision, 12(1):43\u201377.","journal-title":"International Journal of Computer Vision"},{"key":"266550_CR3","doi-asserted-by":"crossref","unstructured":"Beier, T. and Neely, S. 1992. Feature-based image metamorphosis. In SIGGRAPH' 92 Proceedings, Chicago, IL, pp. 35\u201342.","DOI":"10.1145\/133994.134003"},{"key":"266550_CR4","series-title":"Technical Report","volume-title":"Hierarchical motion-based frame rate conversion","author":"J.R. Bergen","year":"1990","unstructured":"Bergen, J.R. and Hingorani, R. 1990. Hierarchical motion-based frame rate conversion. Technical Report, David Sarnoff Research Center, Princeton, New Jersey."},{"key":"266550_CR5","unstructured":"Beymer, D., Shashua, A., and Poggio, T. 1993. Example based image analysis and synthesis. Technical Report 1431, MIT AI Lab."},{"key":"266550_CR6","unstructured":"Black, A. and Taylor, P. 1997. The Festival Speech Synthesis System. University of Edinburgh."},{"key":"266550_CR7","doi-asserted-by":"crossref","unstructured":"Bregler, C., Covell, M., and Slaney, M. 1997. Video rewrite: Driving visual speech with audio. In SIGGRAPH' 97 Proceedings, Los Angeles, CA.","DOI":"10.1145\/258734.258880"},{"issue":"4","key":"266550_CR8","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1109\/TCOM.1983.1095851","volume":"COM-31","author":"P.J. Burt","year":"1983","unstructured":"Burt, P.J. and Adelson, E.H. 1983. The laplacian pyramid as a compact image code. IEEE Trans. on Communications, COM-31(4):532\u2013540.","journal-title":"IEEE Trans. on Communications"},{"key":"266550_CR9","doi-asserted-by":"crossref","unstructured":"Chen, S.E. and Williams, L. 1993. View interpolation for image synthesis. In SIGGRAPH' 93 Proceedings, Anaheim, CA, pp. 279\u2013288.","DOI":"10.1145\/166117.166153"},{"key":"266550_CR10","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1007\/978-4-431-66911-1_13","volume-title":"Models and Techniques in Computer Animation","author":"M.M. Cohen","year":"1993","unstructured":"Cohen, M.M. and Massaro, D.W. 1993. Modeling coarticulation in synthetic visual speech. In N.M. Thalmann and D. Thalmann, (Eds.), Models and Techniques in Computer Animation, Springer-Verlag: Tokyo, pp. 139\u2013156."},{"key":"266550_CR11","doi-asserted-by":"crossref","unstructured":"Cootes, T.F., Edwards, G.J., and Taylor, C.J. 1998. Active appearance models. In Proceedings of the European Conference on Computer Vision, Freiburg, Germany.","DOI":"10.1109\/ICCV.1999.791209"},{"key":"266550_CR12","doi-asserted-by":"crossref","unstructured":"Cosatto, E. and Graf, H. 1998. Sample-based synthesis of photorealistic talking heads. In Proceedings of Computer Animation' 98, Philadelphia, Pennsylvania, pp. 103\u2013110.","DOI":"10.1109\/CA.1998.681914"},{"key":"266550_CR13","unstructured":"Ezzat, T. and Poggio, T. A morphable model for the human mouth. Technical Report, MIT AI Lab, forthcoming."},{"key":"266550_CR14","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1044\/jshr.1104.796","volume":"11","author":"C.G. Fisher","year":"1968","unstructured":"Fisher, C.G. 1968. Confusions among visually perceived consonants. Jour. Speech and Hearing Research, 11:796\u2013804.","journal-title":"Jour. Speech and Hearing Research"},{"key":"266550_CR15","doi-asserted-by":"crossref","unstructured":"Guenter, B., Grimm, C., Wood, D., Malvar, H., and Pighin, F. 1998. Making faces. In SIGGRAPH' 98 Proceedings, Orlando, FL, pp. 55\u201366.","DOI":"10.1145\/280814.280822"},{"key":"266550_CR16","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/0004-3702(81)90024-2","volume":"17","author":"B.K.P. Horn","year":"1981","unstructured":"Horn, B.K.P. and Schunck, B.G. 1981. Determining optical flow. Artificial Intelligence, 17:185\u2013203.","journal-title":"Artificial Intelligence"},{"key":"266550_CR17","unstructured":"Jones, M. and Poggio, T. 1998. Multidimensional morphable models: A framework for representing and maching object classes. In Proceedings of the International Conference on Computer Vision, Bombay, India."},{"key":"266550_CR18","doi-asserted-by":"crossref","unstructured":"Lee, S.Y., Chwa, K.Y., Shin, S.Y., and Wolberg, G. 1992. Image metemorphosis using snakes and free-form deformations. In SIGGRAPH' 92 Proceedings, pp. 439\u2013448.","DOI":"10.1145\/218380.218501"},{"key":"266550_CR19","doi-asserted-by":"crossref","unstructured":"Lee, Y., Terzopoulos, D., and Waters, K. 1995. Realistic modeling for facial animation. In SIGGRAPH' 95 Proceedings, Los Angeles, California, pp. 55\u201362.","DOI":"10.1145\/218380.218407"},{"key":"266550_CR20","doi-asserted-by":"crossref","unstructured":"LeGoff, B. and Benoit, C. 1996. A text-to-audiovisual-speech synthesizer for french. In Proceedings of the International Conference on Spoken Language Processing (ICSLP), Philadelphia, USA.","DOI":"10.21437\/ICSLP.1996-548"},{"key":"266550_CR21","volume-title":"Two-Dimensional Signal and Image Processing","author":"J. Lim","year":"1990","unstructured":"Lim, J. 1990. Two-Dimensional Signal and Image Processing. Prentice Hall: Englewood Cliffs, New Jersey."},{"issue":"6","key":"266550_CR22","doi-asserted-by":"crossref","first-page":"2134","DOI":"10.1121\/1.389537","volume":"73","author":"A. Montgomery","year":"1983","unstructured":"Montgomery, A. and Jackson, P. 1983. Physical characteristics of the lips underlying vowel lipreading performance. Jour. Acoust. Soc. Am., 73(6):2134\u20132144.","journal-title":"Jour. Acoust. Soc. Am."},{"key":"266550_CR23","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1016\/0167-6393(90)90021-Z","volume":"9","author":"E. Moulines","year":"1990","unstructured":"Moulines, E. and Charpentier, F. 1990. Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones. Speech Communication, 9:453\u2013467.","journal-title":"Speech Communication"},{"key":"266550_CR24","volume-title":"Acoustics of American English Speech: A Dynamic Approach","author":"J. Olive","year":"1993","unstructured":"Olive, J., Greenwood, A., and Coleman, J. 1993. Acoustics of American English Speech: A Dynamic Approach. Springer-Verlag: New York, USA."},{"key":"266550_CR25","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1044\/jshr.2803.381","volume":"28","author":"E. Owens","year":"1985","unstructured":"Owens, E. and Blazek, B. 1985. Visemes observed by hearing-impaired and normal-hearing adult viewers. Jour. Speech and Hearing Research, 28:381\u2013393.","journal-title":"Jour. Speech and Hearing Research"},{"key":"266550_CR26","unstructured":"Parke, F.I. 1974. A parametric model of human faces. Ph.D. Thesis, University of Utah."},{"key":"266550_CR27","unstructured":"Pearce, A., Wyvill, B., Wyvill, G., and Hill, D. 1986. Speech and expression: A computer solution to face animation. In Graphics Interface, Vancouver, pp. 136\u2013140."},{"key":"266550_CR28","doi-asserted-by":"crossref","unstructured":"Pighin, F., Hecker, J., Lischinski, D., Szeliski, R., and Salesin, D. 1998. Synthesizing realistic facial expressions from photographs. In SIGGRAPH' 98 Proceedings, Orlando, FL.","DOI":"10.1145\/280814.280825"},{"key":"266550_CR29","first-page":"620","volume":"2","author":"K.C. Scott","year":"1994","unstructured":"Scott, K.C., Kagels, D.S., Watson, S.H., Rom, H., Wright, J.R., Lee, M., and Hussey, K.J. 1994. Synthesis of speaker facial movement to match selected speech sequences. In Proceedings of the Fifth Australian Conference on Speech Science and Technology, Vol. 2, pp. 620\u2013625.","journal-title":"Proceedings of the Fifth Australian Conference on Speech Science and Technology"},{"key":"266550_CR30","doi-asserted-by":"crossref","unstructured":"Seitz, S. and Dyer, C. 1996. View morphing. In SIGGRAPH' 96 Proceedings, pp. 21\u201330.","DOI":"10.1145\/237170.237196"},{"key":"266550_CR31","unstructured":"Waters, K. and Levergood, T. 1993. Decface: An automatic lipsynchronization algorithm for synthetic faces. Technical report, Digital Equipment Corporation CRL Report."},{"key":"266550_CR32","unstructured":"Watson, S.H., Wright, J.R., Scott, K.C., Kagels, D.S., Freda, D., and Hussey, K.J. 1997. An advanced morphing algorithm for interpolating phoneme images to simulate speech. Jet Propulsion Laboratory, California Institute of Technology."},{"key":"266550_CR33","volume-title":"Digital Image Warping","author":"G. Wolberg","year":"1990","unstructured":"Wolberg, G. 1990. Digital Image Warping. IEEE Computer Society Press: Los Alamitos, CA."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1008166717597.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1008166717597\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1008166717597.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T09:57:37Z","timestamp":1754906257000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1008166717597"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2000,6]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2000,6]]}},"alternative-id":["266550"],"URL":"https:\/\/doi.org\/10.1023\/a:1008166717597","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2000,6]]}}}