We present a method for generating realistic
speech-synchronized facial animations using a physics-based
approach and support for coarticulation, i.e. the coloring of a
speech segment by surrounding segments. We have implemented several
extensions to the original coarticulation algorithm of Cohen and
Massaro (M. M. Cohen, D. W. Massaro. Modeling Coarticulation in Synthetic Visual Speech. In Models and Techniques in Computer Animation., pages 139-156. Springer Verlag, Tokyo, 1993). The enhancements include an optimization to
improve performance as well as special treatment of closure and
release phases of bilabial stops and other phonemes. Furthermore, for
phonemes that are shorter than the sampling intervals of the
algorithm and might therefore be missed, additional key frames are
created to ensure their impact onto the animation.
Last modified: Thu Oct 18 09:41:31 CEST 2001 by
Irene Albrecht