HMM-based audio-visual speech recognition integrating geometric and appearance-based visual features.
Michael T. ChanPublished in: MMSP (2001)
Keyphrases
- visual features
- audio visual speech recognition
- multi stream
- visual information
- hidden markov models
- audio visual
- image classification
- image retrieval
- visual content
- image annotation
- visual data
- image search
- visual appearance
- low level features
- object detection
- keywords
- low level
- semantic concepts
- key frames
- image collections
- speech recognition
- saliency map
- video shots
- noisy environments
- computer vision
- image content
- multiscale
- audio features
- image sequences
- image processing