Figure 1
From: Lip-Synching Using Speaker-Specific Articulation, Shape and Appearance Models
A facial animation system generally comprises three modules: the control model that computes a gestural score given the phonetic content of the message to be uttered, a shape model that computes the facial geometry, and an appearance model that computes the final appearance of the face on screen. The acoustic signal can be either postsynchronized or computed by articulatory synthesis. In this later case the internal speech organs shape the vocal tract (tongue, velum, etc.) that is further acoustically "rendered" by appropriate sound sources.