Real-time face animation driven by human voice

This paper presents a review of the recent research that examines the problem of generating full facial animation from auditory input speech signal. The major applications of this technique include face animation, human-computer interfaces, computer-aided instruction, video games and multimedia telephony for the hearing impaired. Using human voice for the real-time animation of synthetic faces remains a challenging area of research in computer animation. The key issue of this research is to find a mapping from audio information to visual information. A variety of approaches can be found in literature. We classify and summarize these approaches and propose a plan for an implementation based on a combination of these approaches.