Audio-to-Visual Conversion Via HMM Inversion for Speech-Driven Facial Animation.
Lucas D. TerissiJuan Carlos GómezPublished in: SBIA (2008)
Keyphrases
- facial animation
- visual speech
- hidden markov models
- visual information
- multi stream
- audio visual
- facial expressions
- speech recognition
- speech signal
- speaker identification
- visual data
- broadcast news
- automatic speech recognition
- temporal coherence
- facial expression recognition
- visual features
- multimedia
- multi modal
- human faces
- emotion recognition
- motion tracking
- active appearance models
- face recognition