{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:50:06Z","timestamp":1778082606110,"version":"3.51.4"},"reference-count":44,"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\/"},{"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\/legal\/tdmrep-license"},{"start":{"date-parts":[[1998,12,23]],"date-time":"1998-12-23T00:00:00Z","timestamp":914371200000},"content-version":"vor","delay-in-days":83,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[1998,10]]},"DOI":"10.1016\/s0167-6393(98)00048-x","type":"journal-article","created":{"date-parts":[[2003,4,4]],"date-time":"2003-04-04T22:57:58Z","timestamp":1049497078000},"page":"23-43","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":270,"title":["Quantitative association of vocal-tract and facial behavior"],"prefix":"10.1016","volume":"26","author":[{"given":"Hani","family":"Yehia","sequence":"first","affiliation":[]},{"given":"Philip","family":"Rubin","sequence":"additional","affiliation":[]},{"given":"Eric","family":"Vatikiotis-Bateson","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"5","key":"10.1016\/S0167-6393(98)00048-X_BIB1","doi-asserted-by":"crossref","first-page":"1535","DOI":"10.1121\/1.381848","article-title":"Inversion of articulatory-to-acoustic transformation in the vocal-tract by a computing sorting technique","volume":"63","author":"Atal","year":"1978","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(98)00048-X_BIB2","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/S0095-4470(95)80044-1","article-title":"Recovery of vocal tract geometry from formants for vowels and fricative consonants using a midsagittal-to-area function conversion model","volume":"23","author":"Badin","year":"1995","journal-title":"Journal of Phonetics"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB3","unstructured":"Carter, J.N., Shadle, C.H., Davis, C.J., 1996. On the use of structured light in speech research. In: Proceedings of The First ESCA Tutorial and Research Workshop on Speech Production Modeling and Fourth Speech Production Seminar, pp. 229\u2013232"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB4","unstructured":"Fant, G., 1960. Acoustic Theory of Speech Production. The Hague"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB5","unstructured":"Hogden, J., 1993. An unsupervised method for learning to track tongue position from ana acoustic signal. Status Report on Speech Research SR-115\/116, Haskins Laboratories, New Haven, CT, USA"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB6","doi-asserted-by":"crossref","unstructured":"Horn, R., Johnson, C., 1985. Matrix Analysis. Cambridge","DOI":"10.1017\/CBO9780511810817"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB7","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1121\/1.1995189","article-title":"Line spectrum representation of linear predictive coefficients of speech signals","volume":"57","author":"Itakura","year":"1975","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(98)00048-X_BIB8","doi-asserted-by":"crossref","first-page":"1356","DOI":"10.1121\/1.410280","article-title":"Determination of sagittal tongue shape from the positions of points on the tongue surface","volume":"56","author":"Kaburagi","year":"1994","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(98)00048-X_BIB9","first-page":"R928","article-title":"Converging evidence in support of common dynamic principles for speech and movement coordination","volume":"15","author":"Kelso","year":"1984","journal-title":"Amer. J. Psychol."},{"key":"10.1016\/S0167-6393(98)00048-X_BIB10","unstructured":"Lin, Q., 1990. Speech production theory and articulatory speech synthesis. Dissertatie, Royal Institute of Technology (KTH), Stockholm"},{"issue":"3,4","key":"10.1016\/S0167-6393(98)00048-X_BIB11","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/0167-6393(82)90017-6","article-title":"A digital simulation method of the vocal-tract system","volume":"1","author":"Maeda","year":"1982","journal-title":"Speech Communication"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB12","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/0167-6393(94)90055-8","article-title":"Recovering articulatory movement from formant frequency trajectories using task dynamics and a genetic algorithm: Preliminary model tests","volume":"14","author":"McGowan","year":"1994","journal-title":"Speech Communication"},{"issue":"5","key":"10.1016\/S0167-6393(98)00048-X_BIB13","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.1121\/1.1910470","article-title":"Determination of vocal-tract shape from measured formant frequencies","volume":"41","author":"Mermelstein","year":"1967","journal-title":"J. Acoust. Soc. Amer."},{"issue":"4","key":"10.1016\/S0167-6393(98)00048-X_BIB14","doi-asserted-by":"crossref","first-page":"1070","DOI":"10.1121\/1.1913427","article-title":"Articulatory model for the study of speech production","volume":"53","author":"Mermelstein","year":"1973","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(98)00048-X_BIB15","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.1121\/1.392790","article-title":"An examination of intra-articulator relative timing","volume":"78","author":"Munhall","year":"1985","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(98)00048-X_BIB16","doi-asserted-by":"crossref","first-page":"1653","DOI":"10.1121\/1.397180","article-title":"Patterns of interarticulator phasing and their relation to linguistic structure","volume":"84","author":"Nittrouer","year":"1988","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(98)00048-X_BIB17","doi-asserted-by":"crossref","first-page":"1528","DOI":"10.1152\/jn.1994.71.4.1528","article-title":"Control of jaw orientation and position in mastication and speech","volume":"71","author":"Ostry","year":"1994","journal-title":"Journal of Neurophysiology"},{"issue":"6","key":"10.1016\/S0167-6393(98)00048-X_BIB18","doi-asserted-by":"crossref","first-page":"3078","DOI":"10.1121\/1.404204","article-title":"Electromagnetic midsagittal articulometer systems for transducing speech articulatory movements","volume":"92","author":"Perkell","year":"1992","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(98)00048-X_BIB19","unstructured":"Rabiner, L., Juang, B.W., 1993. Fundamentals of Speech Recognition. Prentice-Hall, Englewood Cliffs, NJ"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB20","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1121\/1.386780","article-title":"An articulatory synthesizer for perceptual research","volume":"70","author":"Rubin","year":"1981","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(98)00048-X_BIB21","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"},{"issue":"4","key":"10.1016\/S0167-6393(98)00048-X_BIB22","doi-asserted-by":"crossref","first-page":"1002","DOI":"10.1121\/1.1910429","article-title":"Determination of the geometry of the human vocal-tract by acoustical measurements","volume":"41","author":"Schroeder","year":"1967","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(98)00048-X_BIB23","unstructured":"Schroeter, J., Sondhi, M., 1991. Speech coding based on physiological models of speech production. In: Sondhi, M.M., Furui, S. (Eds.), Advances in Speech Processing. Marcel Dekker, New York, pp. 231\u2013268"},{"issue":"1","key":"10.1016\/S0167-6393(98)00048-X_BIB24","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1109\/89.260356","article-title":"Techniques for estimating vocal-tract shapes from the speech signal","volume":"2","author":"Schroeter","year":"1994","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(98)00048-X_BIB25","doi-asserted-by":"crossref","unstructured":"Scully, C., 1990. Articulatory synthesis. In: Hardcastle, W.J., Marchal, A. (Eds.), Speech Production and Speech Modelling. Kluwer Academic Publishers, Dordrecht, pp. 151\u2013186","DOI":"10.1007\/978-94-009-2037-8_7"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB26","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/0167-6393(93)90058-S","article-title":"Estimation and generation of articulatory motion using neural networks","volume":"13","author":"Shirai","year":"1993","journal-title":"Speech Communication"},{"issue":"7","key":"10.1016\/S0167-6393(98)00048-X_BIB27","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1109\/TASSP.1987.1165240","article-title":"A hybrid time-frequency domain articulatory speech synthesizer","volume":"35","author":"Sondhi","year":"1987","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"3","key":"10.1016\/S0167-6393(98)00048-X_BIB28","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1121\/1.1907943","article-title":"Development of a quantitative description of vowel articulation","volume":"27","author":"Stevens","year":"1955","journal-title":"J. Acoust. Soc. Amer."},{"issue":"5","key":"10.1016\/S0167-6393(98)00048-X_BIB29","doi-asserted-by":"crossref","first-page":"2207","DOI":"10.1121\/1.399188","article-title":"A three-dimensional model of tongue movement based on ultrasound and X-ray microbeam data","volume":"87","author":"Stone","year":"1990","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(98)00048-X_BIB30","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/0167-6393(86)90008-7","article-title":"Speech analysis and synthesis methods developed at ECL in NTT \u2013 From LPC to LSP \u2013","volume":"5","author":"Sugamura","year":"1986","journal-title":"Speech Communication"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB31","unstructured":"Tiede, M.K., Vatikiotis-Bateson, E., 1994. Extracting articulator movement parameters from a videodisc-based cineradiographic database. In: Proc. International Conference on Spoken Language Processing, pp. S02-4.1\u2013S02-4.4"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB32","doi-asserted-by":"crossref","unstructured":"Vatikiotis-Bateson, E., Ostry, D.J., 1995. An analysis of the dimensionality of jaw motion in speech. Journal of Phonetics 23, 101\u2013117","DOI":"10.1016\/S0095-4470(95)80035-2"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB33","unstructured":"Vatikiotis-Bateson, E., Yehia, H., 1996. Physiological modeling of facial motion during speech. H-96 65, The Acoustical Society of Japan."},{"key":"10.1016\/S0167-6393(98)00048-X_BIB34","doi-asserted-by":"crossref","unstructured":"Vatikiotis-Bateson, E., Yehia, H.C., 1997. Unified physiological model of audible-visible speech production. In: Fifth European Conference on Speech Communication and Technology","DOI":"10.21437\/Eurospeech.1997-538"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB35","doi-asserted-by":"crossref","unstructured":"Vatikiotis-Bateson, E., Munhall, K.G., Kasahara Y., Garcia, F., Yehia, H., 1996a. Characterizing audiovisual information during speech. In: Proceedings of the International Conference on Spoken Language Processing, pp. 1485\u20131488","DOI":"10.21437\/ICSLP.1996-379"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB36","doi-asserted-by":"crossref","unstructured":"Vatikiotis-Bateson, E., Munhall, K.G., Hirayama, M., Lee, Y.C., Terzopoulos, D., 1996b. The dynamics of audiovisual behavior in speech. In: Stork, D., Hennecke, M. (Eds.), Speech Reading by Humans and Machines, Vol. 150, NATO-ASI Series, Series F, Computers and Systems Sciences. Springer, Berlin, pp. 221\u2013232","DOI":"10.1007\/978-3-662-13015-5_16"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB37","unstructured":"Vatikiotis-Bateson, E., Kuratate, T., Tiede, M.K., Yehia, H.C., 1998. Kinematics-based synthesis of realistic talking faces. Technical Report TR-H-237, ATR-HIP"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB38","doi-asserted-by":"crossref","unstructured":"Yehia, H., Itakura, F., 1994. Determination of human vocal-tract dynamic geometry from formant trajectories using spatial and temporal Fourier analysis. In: Proc. IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 477\u2013480","DOI":"10.1109\/ICASSP.1994.389252"},{"issue":"2","key":"10.1016\/S0167-6393(98)00048-X_BIB39","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/0167-6393(95)00042-9","article-title":"A method to combine acoustical and morphological constraints in the speech production inverse problem","volume":"18","author":"Yehia","year":"1996","journal-title":"Speech Communication"},{"issue":"D-8","key":"10.1016\/S0167-6393(98)00048-X_BIB40","first-page":"1198","article-title":"An acoustically oriented vocal-tract model","volume":"E79","author":"Yehia","year":"1996","journal-title":"IEICE Transactions on Information and Systems"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB41","unstructured":"Yehia, H., Takeda, K., Itakura, F., in review. An analysis of the acoustic-to-articulatory mapping during speech under morphological and continuity constraints. Speech Communication"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB42","unstructured":"Yehia, H.C., Rubin, P., Vatikiotis-Bateson, E., 1997. Quantitative association of orofacial and vocal-tract shapes. In: European Tutorial and Research Workshop on Audio-Visual Speech Processing: Computational and Cognitive Science Approaches"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB43","unstructured":"Zacks, S., 1971. The Theory of Statistical Inference. Wiley, New York"},{"key":"10.1016\/S0167-6393(98)00048-X_BIB44","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1006\/csla.1994.1009","article-title":"A new neural network for articulatory speech recognition and its application to vowel identification","volume":"8","author":"Zacks","year":"1994","journal-title":"Computer Speech and Language"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S016763939800048X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S016763939800048X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T22:37:38Z","timestamp":1759099058000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S016763939800048X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998,10]]},"references-count":44,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[1998,10]]}},"alternative-id":["S016763939800048X"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(98)00048-x","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[1998,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Quantitative association of vocal-tract and facial behavior","name":"articletitle","label":"Article Title"},{"value":"Speech Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/S0167-6393(98)00048-X","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"converted-article","name":"content_type","label":"Content Type"},{"value":"Copyright \u00a9 1998 Elsevier Science B.V. All rights reserved.","name":"copyright","label":"Copyright"}]}}