Hidden Markov Model Inversion for Audio-to-Visual Conversion in an MPEG-4 Facial Animation System.
Kyoung-Ho ChoiYing LuoJenq-Neng HwangPublished in: J. VLSI Signal Process. (2001)
Keyphrases
- hidden markov models
- facial animation
- visual speech
- visual information
- facial expressions
- multimedia
- speech recognition
- visual data
- visual features
- multi stream
- temporal coherence
- human faces
- active appearance models
- facial expression recognition
- face model
- facial images
- conditional random fields
- audio visual
- gesture recognition
- motion tracking
- emotion recognition
- head motion
- motion capture data
- speech signal
- face detection
- video sequences
- image segmentation