A Multi-Scale Feature Aggregation Based Lightweight Network for Audio-Visual Speech Enhancement.
Haitao XuLiangfa WeiJie ZhangJianming YangYannan WangTian GaoXin FangLi-Rong DaiPublished in: ICASSP (2023)
Keyphrases
- lightweight
- audio visual
- multiscale
- multi modal
- communication infrastructure
- wireless sensor networks
- speech enhancement
- visual information
- feature set
- multi stream
- edge detection
- multimedia
- visual data
- speech signal
- image features
- feature vectors
- image representation
- image segmentation
- communication networks
- audio features
- low level
- machine learning
- pattern recognition
- image processing
- metadata
- information retrieval