Visual Speech Synthesis by Morphing Visemes
We present MikeTalk, a text-to-audiovisual speech synthesizer which converts input text into an audiovisual speech stream. MikeTalk is built using visemes, which are a small set of images spanning a large range of mouth shapes. The visemes are acquired from a recorded visual corpus of a human subjec...
Main Authors: | Ezzat, Tony, Poggio, Tomaso |
---|---|
语言: | en_US |
出版: |
2004
|
在线阅读: | http://hdl.handle.net/1721.1/7263 |
相似书籍
-
Modeling continuous visual speech using boosted viseme models
由: Dong, Liang, et al.
出版: (2009) -
Perceptual Evaluation of Video-Realistic Speech
由: Geiger, Gadi, et al.
出版: (2004) -
Cross-speaker viseme mapping using hidden Markov models
由: Dong, Liang, et al.
出版: (2009) -
Synthesis of Visual Modules from Examples: Learning Hyperacuity
由: Poggio, Tomaso, et al.
出版: (2004) -
Visual Algorithms
由: Poggio, Tomaso
出版: (2004)