Rule-Structured Facial Animation System

Abstract

Our overall goal is to produce as automatic as possible facial expressions with wrinkles from spoken input. We focus on two aspects of this problem: integration of the expressive wrinkles and generation of synchronized speechanimation. Our facial model integrates facial muscles deformations and bulges. We have produced a high level programming language to automatically drive 3D animation of facial expressions from speech. Our system embodies rule-governed translation from speech and utterance meaning to facial expressions. We are concerned primarily with expressions conveying information correlated with the intonation of the voice, some of which are also correlated with affect or emotion. We apply our automatic animation model to a new facial animation system which integrates effects of the facial motion as expressive wrinkles and muscles dependencies. We obtain then with this subtle criteria of modeling and motion an animation much more expressive and natural.