Improving lip-reading with feature space transforms for multi-stream audio-visual speech recognition.
Jing HuangKarthik VisweswariahPublished in: INTERSPEECH (2005)
Keyphrases
- audio visual speech recognition
- multi stream
- feature space
- visual speech
- hidden markov models
- audio visual
- high dimensional
- feature extraction
- feature vectors
- feature selection
- speech recognition
- low dimensional
- dimensionality reduction
- principal component analysis
- speaker identification
- image sequences
- image representation
- visual words
- noisy environments
- data points
- computer vision