SMMA-Net: An Audio Clue-Based Target Speaker Extraction Network with Spectrogram Matching and Mutual Attention.
Ying HuHaitao XuZhongcun GuoHao HuangLiang HePublished in: ICASSP (2024)
Keyphrases
- audio visual
- computer networks
- wireless sensor networks
- automatic speech recognition
- multimedia
- matching algorithm
- information extraction
- prosodic features
- signal processing
- network structure
- complex networks
- network traffic
- shape matching
- pattern analysis
- speaker identification
- automatic transcription
- peer to peer
- communication networks
- visual data