Deep Audio-Visual Speech Separation with Attention Mechanism.
Chenda LiYanmin QianPublished in: ICASSP (2020)
Keyphrases
- audio visual
- attention mechanism
- multi modal
- visual attention
- video summarization
- visual attention model
- sound source
- multi stream
- emotion recognition
- saliency map
- visual information
- visual data
- audio features
- audio visual speech recognition
- multimedia
- eye tracking
- image processing
- image content
- higher level
- vision system
- spatio temporal
- object recognition
- information retrieval