Audio-visual speech modeling using coupled hidden Markov models.
Stephen M. ChuThomas S. HuangPublished in: ICASSP (2002)
Keyphrases
- hidden markov models
- audio visual
- multi stream
- multi modal
- speech recognition
- audio visual speech recognition
- multimedia
- visual information
- gesture recognition
- emotion recognition
- automatic speech recognition
- speaker verification
- digit recognition
- visual data
- sequential data
- phoneme recognition
- facial expressions
- spatio temporal
- high dimensional
- linear dynamical systems