Dual Attention for Audio-Visual Speech Enhancement with Facial Cues.
Fexiang WangShuang YangShiguang ShanXilin ChenPublished in: BMVC (2023)
Keyphrases
- audio visual
- emotion recognition
- speech enhancement
- multimodal fusion
- multi modal
- visual information
- noisy environments
- noise reduction
- facial expressions
- speaker verification
- single channel
- signal to noise ratio
- visual data
- multi stream
- multimedia
- speech signal
- face recognition
- linear prediction
- background noise
- focus of attention
- data analysis
- non stationary
- face images
- video sequences
- vocal tract