Multi-scale speaker embedding-based graph attention networks for speaker diarisation.
Youngki KwonHee-Soo HeoJee-weon JungYou Jin KimBong-Jin LeeJoon Son ChungPublished in: CoRR (2021)
Keyphrases
- multiscale
- speaker verification
- audio visual
- speech recognition
- speaker diarization
- speaker recognition
- social networks
- graph theoretic
- graph model
- automatic speech recognition
- speaker identification
- average degree
- natural images
- random walk
- edge detection
- complex networks
- visual attention
- graph matching
- graph representation
- semi supervised