Speech to lip movement synthesis by HMM.
Eli YamamotoSatoshi NakamuraKiyohiro ShikanoPublished in: AVSP (1997)
Keyphrases
- speech recognition
- hidden markov models
- visual speech
- multi stream
- speech signal
- audio visual speech recognition
- visual speech recognition
- automatic speech recognition systems
- automatic speech recognition
- lip reading
- speaker identification
- recognition engine
- phoneme recognition
- keyword spotting
- speaker adaptation
- speaker independent
- speech synthesis
- audio visual
- noisy environments
- texture synthesis
- pattern recognition
- program synthesis
- speech recognizer
- handwritten word recognition
- audio signals
- text to speech
- facial animation
- speaker recognition
- conditional random fields
- acoustic features
- finite state transducers
- broadcast news
- spoken language
- language acquisition
- non stationary
- multi modal
- hierarchical hidden markov model