Cooperative Dual Attention for Audio-Visual Speech Enhancement with Facial Cues.
Feixiang WangShuang YangShiguang ShanXilin ChenPublished in: CoRR (2023)
Keyphrases
- audio visual
- emotion recognition
- speech enhancement
- multimodal fusion
- multi modal
- noisy environments
- visual information
- signal to noise ratio
- noise reduction
- multi stream
- multimedia
- linear prediction
- visual data
- speaker verification
- speech signal
- facial expressions
- wiener filter
- single channel
- prior knowledge
- face recognition
- image restoration
- multiscale
- audio features
- vocal tract
- smoothing algorithm
- image sequences
- pattern recognition