Automatic lips reading for audio-visual speech processing and recognition.
Josef ChaloupkaPublished in: INTERSPEECH (2004)
Keyphrases
- audio visual
- speech processing
- multi modal
- signal processing
- multimedia systems
- speaker identification
- speech recognition
- multimedia
- natural language processing
- audio features
- pattern recognition
- visual data
- feature extraction
- visual information
- visual speech
- artificial intelligence
- english text
- image processing
- information retrieval
- action recognition