ESCA Workshop on Audio-Visual Speech Processing (AVSP'97) September 26-27, 1997 Rhodes, Greece

Quantitative Association of Orofacial and Vocal-Tract Shapes

Hani Yehia (1), Philip Rubin (2), Eric Vatikiotis-Bateson (1)

(1) ATR Human Information Research Laboratories, Soraku-gun, Kyoto, Japan
(2) Haskins Laboratories, New Haven, USA

This paper examines the degrees of correlation among vocal tract and orofacial movement data and the speech acoustics. Multilinear techniques are applied to support the claims that orofacial motion during speech is largely a by-product of producing the speech acoustics and further that the spectral envelope of the speech acoustics is better estimated by the 3D motion of the face than the mid-sagittal motion of the anterior vocal tract (lips, tongue, and jaw).

Full Paper

Bibliographic reference.  Yehia, Hani / Rubin, Philip / Vatikiotis-Bateson, Eric (1997): "Quantitative association of orofacial and vocal-tract shapes", In AVSP-1997, 41-44.