Bayesian separation of audio-visual speech sources.
Shyamsundar RajaramAra V. NefianThomas S. HuangPublished in: ICASSP (5) (2004)
Keyphrases
- visual speech
- hidden markov models
- audio visual speech recognition
- visual speech recognition
- speaker identification
- audio signals
- noisy environments
- lip reading
- audio signal
- video signals
- multi stream
- maximum likelihood
- speech signal
- multimedia
- broadcast news
- speech recognition
- bayesian networks
- text to speech
- gaussian mixture model
- keywords