{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T06:17:21Z","timestamp":1763619441246,"version":"3.30.1"},"reference-count":42,"publisher":"Elsevier BV","issue":"1-2","license":[{"start":{"date-parts":[[1998,10,1]],"date-time":"1998-10-01T00:00:00Z","timestamp":907200000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[1998,10]]},"DOI":"10.1016\/s0167-6393(98)00045-4","type":"journal-article","created":{"date-parts":[[2003,4,5]],"date-time":"2003-04-05T03:57:58Z","timestamp":1049515078000},"page":"117-129","source":"Crossref","is-referenced-by-count":31,"title":["Audio-visual speech synthesis from French text: Eight years of models, designs and evaluation at the ICP"],"prefix":"10.1016","volume":"26","author":[{"given":"Christian","family":"Beno\u0131\u0302t","sequence":"first","affiliation":[]},{"given":"Bertrand","family":"Le Goff","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(98)00045-4_BIB1","unstructured":"Abry, C., Lallouache, M.T., 1991. Audibility and stability of articulatory movements: Deciphering two experiments on anticipatory rounding in French. In: Proceedings of the XIIth International Congress of Phonetic Sciences, Aix-en-Provence, France, Vol. 1, pp. 220\u2013225"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB2","unstructured":"Adjoudani, A., 1993. Elaboration d'un mod\u00e8le de l\u00e8vres 3D pour animation en temps r\u00e9el. M\u00e9moire de DEA SIP, INPG, Grenoble, France"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB3","unstructured":"Alissali, M., 1993. Architecture logicielle pour la synth\u00e8se multilingue de la parole, PhD Thesis. Institut National Polytechnique, Grenoble, France"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB4","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/S0167-6393(97)00025-3","article-title":"Learning to speak. Sensori-motor control of speech movements","volume":"22","author":"Bailly","year":"1997","journal-title":"Speech Communication"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB5","unstructured":"Bailly, G., Guerti, M., 1991. Synthesis-by-rule for French. In: Proceedings of the 12th International Congress of Phonetic Sciences, Aix-en-Provence, France, Vol. 2, pp. 506\u2013511"},{"issue":"4","key":"10.1016\/S0167-6393(98)00045-4_BIB6","first-page":"359","article-title":"COMPOST: a server for multilingual text-to-speech system","volume":"9","author":"Bailly","year":"1992","journal-title":"Traitement du Signal"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB7","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1159\/000259479","article-title":"Coarticulation of upper lip protrusion in French","volume":"30","author":"Benguerel","year":"1974","journal-title":"Phonetica"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB8","unstructured":"Beno\u0131\u0302t, C., Lallouache, T., Mohamadi, T., Abry, C., 1992. A set of French visemes for visual speech synthesis. In: Bailly, G., Beno\u0131\u0302t, C (Eds.), Talking Machines: Theories, Models and Designs. Elsevier, Amsterdam, pp. 485\u2013504"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB9","doi-asserted-by":"crossref","first-page":"1195","DOI":"10.1044\/jshr.3705.1195","article-title":"Audio-visual intelligibility of French speech in noise","volume":"37","author":"Beno\u0131\u0302t","year":"1994","journal-title":"Journal of Speech and Hearing Research"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB10","unstructured":"Beno\u0131\u0302t, C., Fuster-Duran, A., Le Goff, B., 1996a. An investigation of hypo- and hyper-speech in the visual modality. In: Proceedings of ETRW 96, Autrans, France, pp. 237\u2013240"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB11","doi-asserted-by":"crossref","unstructured":"Beno\u0131\u0302t, C., Guiard-Marigny, T., Le Goff, B., Adjoudani, A., 1996b. Which components of the face do humans and machines best speechread?. In: Stork, D., Hennecke, M. (Eds.), Speechreading by Humans and Machines, NATO-ASI Series 150 Springer, Berlin, pp. 315\u2013328","DOI":"10.1007\/978-3-662-13015-5_24"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB12","doi-asserted-by":"crossref","unstructured":"Beno\u0131\u0302t, C., Adjoudani, A., Guiard-Marigny, T., Le Goff, B., Reveret, L., 1997. A multimedia platform for audio-visual speech processing. In: Proceedings of the 5th Eurospeech Conference, ESCA, Rhodes, Greece, Vol. 3, pp. 1671\u20131674","DOI":"10.21437\/Eurospeech.1997-476"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB13","doi-asserted-by":"crossref","unstructured":"Beskow, J., 1995. Rule-based visual speech synthesis. In: Proceedings of Eurospeech`95, Madrid, Spain, Vol. 1, pp. 299\u2013302","DOI":"10.21437\/Eurospeech.1995-81"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB14","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/S0095-4470(19)30777-6","article-title":"Analysis, synthesis and perception of visible articulatory movements","volume":"11","author":"Brooke","year":"1983","journal-title":"Journal of Phonetics"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB15","doi-asserted-by":"crossref","unstructured":"Charpentier, F., Moulines, E., 1989. Pitch-synchronous waveform processing technique for text-to-speech synthesis using diphones. In: Proceedings of the First Eurospeech Conference, ESCA, Paris, France, Vol. 2, pp. 13\u201319","DOI":"10.21437\/Eurospeech.1989-172"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB16","doi-asserted-by":"crossref","first-page":"260","DOI":"10.3758\/BF03203157","article-title":"Synthesis of visible speech","volume":"22","author":"Cohen","year":"1990","journal-title":"Behavior Research Methods, Instruments and Computers"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB17","doi-asserted-by":"crossref","unstructured":"Cohen, M.M., Massaro, D.W., 1993. Modeling coarticulation in synthetic visual speech. Models and techniques. In: Thalmann, N.M., Thalmann, D. (Eds.), Computer Animation. Springer, Tokyo, pp. 139\u2013156","DOI":"10.1007\/978-4-431-66911-1_13"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB18","first-page":"3","article-title":"Cued speech","volume":"112","author":"Cornett","year":"1967","journal-title":"American Annals of the Deaf"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB19","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1044\/jshr.1202.423","article-title":"Interaction of audition and vision in the recognition of oral speech stimuli","volume":"12","author":"Erber","year":"1969","journal-title":"Journal of Speech and Hearing Research"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB20","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1044\/jshd.4004.481","article-title":"Auditory\u2013visual perception of speech","volume":"40","author":"Erber","year":"1975","journal-title":"Journal of Speech and Hearing Research"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB21","first-page":"474","article-title":"Confusion among visually perceived consonants","volume":"15","author":"Fisher","year":"1968","journal-title":"Journal of Speech and Hearing Research"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB22","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1037\/0096-3445.112.3.386","article-title":"Converging sources of evidence on spoken and perceived rhythms of speech: Cyclic production of vowels in monosyllabic stress feet","volume":"112","author":"Fowler","year":"1983","journal-title":"Journal of Experimental Psychology: Human Perception and Performance"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB23","unstructured":"Guiard-Marigny, T., 1992. Animation en temps r\u00e9el d'un mod\u00e8le param\u00e9tris\u00e9 de l\u00e8vres. M\u00e9moire de DEA SIP, INPG, Grenoble, France, p. 72"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB24","doi-asserted-by":"crossref","unstructured":"Guiard-Marigny, T., Adjoudani, A., Beno\u0131\u0302t, C., 1996. 3D models of the lips and jaw for visual speech synthesis. In: van Santen, J.P.H., Sproat, R., Olive, J., Hirshberg, J. (Eds.), Progress in Speech Synthesis. Springer, New York, pp. 247\u2013258","DOI":"10.1007\/978-1-4612-1894-4_19"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2307\/522229","article-title":"Acoustic phonetics","volume":"24","author":"Joos","year":"1948","journal-title":"Language"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB26","unstructured":"Le Goff, B., 1993. Commandes param\u00e9triques d'un mod\u00e8le de visage 3D pour animation en temps r\u00e9el. M\u00e9moire de DEA SIP, INPG, Grenoble, France"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB27","doi-asserted-by":"crossref","unstructured":"Le Goff, B., 1997a. Automatic modeling of coarticulation in text-to-visual speech synthesis. In: Proceedings of the 5th Eurospeech Conference, ESCA, Rhodes, Greece, Vol. 3, pp. 1667\u20131670","DOI":"10.21437\/Eurospeech.1997-475"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB28","unstructured":"Le Goff, B., 1997b. Synth\u00e8se \u00e0 partir du texte de visage 3D parlant fran\u00e7ais. M\u00e9moire de th\u00e8se, INP, Grenoble, France, p. 256"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB29","doi-asserted-by":"crossref","unstructured":"Le Goff, B., Beno\u0131\u0302t, C., 1996. A text-to-audiovisual-speech synthesizer for French. In: Proceedings of the 4th International Conference on Spoken Language Processing, Philadelphia, PA, USA, Vol. 4, pp. 2163\u20132166","DOI":"10.1109\/ICSLP.1996.607232"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB30","unstructured":"Le Goff, B., Beno\u0131\u0302t, C., 1997. A French-speaking synthetic head. In: Beno\u0131\u0302t, C., Campbell, R. (Eds.), Proceedings of the ESCA workshop on Audio-Visual Speech Processing, Rhodes, Greece, pp. 145\u2013148"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB31","doi-asserted-by":"crossref","unstructured":"Le Goff, B., Guiard-Marigny, T., Beno\u0131\u0302t, C., 1996. Analysis-synthesis and intelligibility of a talking face. In: Van Santen, J.P.H., Sproat, R.W., Olive, J.P., J. Hirschberg (Eds.), Progress in Speech Synthesis. Springer. New York, pp. 235\u2013246","DOI":"10.1007\/978-1-4612-1894-4_18"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB32","doi-asserted-by":"crossref","unstructured":"L\u00f6fquist, A., 1990. Speech as audible gestures. In: Hardcastle, W.J., Marchal, A. (Eds.), Speech Production and Speech Modeling. Kluwer Academic Publishers, Dordrecht, pp. 289\u2013322","DOI":"10.1007\/978-94-009-2037-8_12"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB33","unstructured":"Massaro, D.W., 1997. Perceiving Talking Faces. MIT Press, Cambridge, MA"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB34","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1038\/264746a0","article-title":"Hearing lips and seeing voices","volume":"264","author":"McGurk","year":"1976","journal-title":"Nature"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB35","unstructured":"Mohamadi, T., 1993. Synth\u00e8se \u00e0 partir du texte de visages parlants: R\u00e9alisation d'un prototype et mesures d'intelligibilit\u00e9 bimodale. M\u00e9moire de th\u00e8se, INP, Grenoble, 174 pp."},{"key":"10.1016\/S0167-6393(98)00045-4_BIB36","unstructured":"Parke, F.I., 1974. A parametric model for human faces. Ph.D Dissertation, University of Utah, Department of Computer Sciences"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB37","unstructured":"Saintourens, M., Tramus, M.H., Huitric, H., Nahas, M., 1990. Creation of a synthetic face speaking in real time with a synthetic voice. In: Beno\u0131\u0302t, C., Bailly, G. (Eds.), Proceedings of the 1st ESCA Workshop on Speech Synthesis, Autrans, France, pp. 249\u2013252"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB38","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1207\/s15326969eco0104_2","article-title":"A dynamical approach to gestural patterning in speech production","volume":"1","author":"Saltzman","year":"1989","journal-title":"Ecological Psychology"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB39","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1121\/1.1907309","article-title":"Visual contribution to speech intelligibility in noise","volume":"26","author":"Sumby","year":"1954","journal-title":"Journal of the Acoustical Society of America"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB40","doi-asserted-by":"crossref","unstructured":"Summerfield, Q., MacLeod, A., McGrath, M., Brooke, M., 1989. Lips, teeth, and the benefits of lipreading. In: Young, A.W., Ellis, H.D. (Eds.), Handbook of Research on Face Processing. Elsevier, Amsterdam, pp. 223\u2013233","DOI":"10.1016\/B978-0-444-87143-5.50019-6"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB41","unstructured":"Woodward, P., 1991. Synth\u00e8se de visage parlant. DEA Dissertation, ENSERG, INP Grenoble"},{"key":"10.1016\/S0167-6393(98)00045-4_BIB42","unstructured":"Woodward, P., Mohamadi, T., Beno\u0131\u0302t, C., Bailly, G., 1992. Synth\u00e8se \u00e0 partir du texte d'un visage parlant fran\u00e7ais. Actes des 19\u00e8mes Journ\u00e9es dEtude sur la Parole, GFCP-SFA, Brussels, Belgium, pp. 319\u2013324"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639398000454?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639398000454?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T04:21:54Z","timestamp":1733458914000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639398000454"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998,10]]},"references-count":42,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[1998,10]]}},"alternative-id":["S0167639398000454"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(98)00045-4","relation":{},"ISSN":["0167-6393"],"issn-type":[{"type":"print","value":"0167-6393"}],"subject":[],"published":{"date-parts":[[1998,10]]}}}