Lip-sync animation from HMM using dynamic features.
Tatsuo YotsukuraShinichi KawamotoSatoshi NakamuraPublished in: SIGGRAPH Research Posters (2006)
Keyphrases
- hidden markov models
- visual speech recognition
- handwritten word recognition
- computer graphics
- computer animation
- speech recognition
- visual speech
- motion capture
- hierarchical hidden markov model
- computer vision
- user interface
- multi stream
- machine learning
- database
- lip reading
- pattern recognition
- gesture recognition
- bayesian networks
- motion capture data
- image processing
- forward backward
- special effects
- keyword spotting
- data sets