Large Vocabulary Audio-Visual Speech Recognition Using Active Shape Models.
Tanveer A. FaruquieAbhik MajumdarNitendra RajputL. Venkata SubramaniamPublished in: ICPR (2000)
Keyphrases
- audio visual
- active shape model
- multi modal
- shape model
- coarse to fine
- multi stream
- segmentation algorithm
- visual information
- emotion recognition
- speech recognition
- facial features
- audio features
- visual data
- object boundaries
- audio visual speech recognition
- shape prior
- active appearance models
- random forest
- appearance model
- pattern recognition
- training data
- noisy environments
- eye movements
- speaker identification
- low level