Joint audio-visual speech processing for recognition and enhancement.
Gerasimos PotamianosChalapathy NetiSabine DelignePublished in: AVSP (2003)
Keyphrases
- audio visual
- speech processing
- multi modal
- speech recognition
- signal processing
- multimedia
- multimedia systems
- visual information
- visual data
- speaker identification
- pattern recognition
- natural language processing
- artificial intelligence
- feature extraction
- english text
- action recognition
- audio features
- machine learning
- noisy environments
- activity recognition
- sound source
- video data
- knn