1st ETRW on Speech Production Modeling: From Control Strategies to Acoustics 4th Speech Production Seminar: Models and Data Autrans, France May 20-24, 1996

Physiology-Based Synthesis of Audiovisual Speech

Eric Vatikiotis-Bateson (1), Kevin G. Munhall (2), M. Hirayama (3), Y. Kasahara (4), H. Yehia (1)

(1) ATR Human Information Processing Res. Labs., Kyoto, Japan
(2) Queen's University, Kingston, Canada
(3) Hewlett-Packard Res. Labs., Yokohama, Japan
(4) Waseda University, Tokyo, Japan

In this paper, several analyses relating facial motion with perioral muscle behavior and speech acoustics are described. The results suggest that linguistically relevant visual information is distributed over large regions of the face and can be modeled from the same control source as the acoustics.

Full Paper

Bibliographic reference.  Vatikiotis-Bateson, Eric / Munhall, Kevin G. / Hirayama, M. / Kasahara, Y. / Yehia, H. (1996): "Physiology-based synthesis of audiovisual speech", In SPM-1996, 241-244.