Using viseme based acoustic models for speech driven lip synthesis.
Ashish VermaNitendra RajputL. Venkata SubramaniamPublished in: ICASSP (5) (2003)
Keyphrases
- acoustic models
- hidden markov models
- visual speech
- speech recognition
- broadcast news
- speaker identification
- speaker independent
- speech signal
- automatic speech recognition
- noisy environments
- discriminative training
- speech recognizer
- video search
- neural network
- speaker verification
- audio signals
- acoustic features
- gaussian mixture model
- pattern recognition