On optimal selection of lip-motion features for speaker identification.
Hasan Ertan ÇetingülEngin ErzinYücel YemezA. Murat TekalpPublished in: MMSP (2004)
Keyphrases
- motion features
- speaker identification
- optimal selection
- motion analysis
- speech recognition
- activity recognition
- gaussian mixture model
- action recognition
- video data
- visual features
- motion patterns
- speech signal
- noisy environments
- video shots
- broadcast news
- optical flow
- motion vectors
- feature extraction
- motion model
- depth images
- human actions
- shape features
- audio features
- image classification
- image sequences
- visual information
- visual content
- video retrieval
- information retrieval
- mixture model
- hidden markov models
- similarity measure
- learning algorithm