Lip Movement Synthesis from Speech Based on Hidden Markov Models.
Eli YamamotoSatoshi NakamuraKiyohiro ShikanoPublished in: FG (1998)
Keyphrases
- hidden markov models
- visual speech
- speech recognition
- visual speech recognition
- speech signal
- phoneme recognition
- automatic speech recognition
- lip reading
- multi stream
- speaker independent
- keyword spotting
- automatic speech recognition systems
- gesture recognition
- markov models
- speaker identification
- hidden state
- audio signals
- speech processing
- discriminative training
- viterbi algorithm
- baum welch
- sequence classification
- hidden states
- text recognition
- sequential data
- markov model
- facial motion
- random effects
- speech recognizer
- speaker dependent
- conditional random fields
- spoken language
- broadcast news
- facial animation