Optimizing Audio-Visual Speech Enhancement Using Multi-Level Distortion Measures for Audio-Visual Speech Recognition.
Hang ChenQing WangJun DuBao-Cai YinJia PanChin-Hui LeePublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2024)
Keyphrases
- audio visual speech recognition
- audio visual
- noisy environments
- multi stream
- multi modal
- multimedia
- noise reduction
- visual data
- speaker verification
- visual information
- speech recognition
- information retrieval
- emotion recognition
- speech signal
- audio features
- image classification
- image sequences
- visual speech
- computer vision