“Speech to talking heads system based on hidden Markov models” by Yotsukura, Morishima and Nakamura
Conference:
Type:
Title:
- Speech to talking heads system based on hidden Markov models
Presenter(s)/Author(s):
Abstract:
This paper describes a technique to create human-like talking head speech animation with levels of naturalness and realism by mapping from speech information to facial movement sequences. Speech animation techniques for human-like natural talking head systems have traditionally included both key-framing methods [Cohen and Massaro 1993]and physics-based methods[Waters 1987]. Recent machine learning methods provide a new technique for speech animation systems
References:
1. Cohen, M. M., Massaro, D. W. 1993. Modeling coarticulation in synthetic visual speech. Models and Techniques in Computer Animation, pp. 139–156.
2. Yamamoto, E., Nakamura, S., Shikano, K. 1998. Lip movement synthesis from speech based on hidden markov models. Speech Communication, pp. 105–115
3. Waters, K. 1987. A muscle model for animating three-dimensional facial expressions. ACM SIGGRAPH 87, pp. 17–24.
