Multi-Scale Speaker Embedding-Based Graph Attention Networks For Speaker Diarisation.
Youngki KwonHee-Soo HeoJee-Weon JungYou Jin KimBong-Jin LeeJoon Son ChungPublished in: ICASSP (2022)
Keyphrases
- multiscale
- speaker verification
- audio visual
- speaker recognition
- speech recognition
- speaker identification
- random walk
- social networks
- automatic speech recognition
- scale space
- speaker diarization
- directed graph
- visual attention
- bipartite graph
- image processing
- graph embedding
- graph structure
- graph theory
- spanning tree
- graph theoretic
- small world
- graph matching
- community discovery
- gaussian mixture model
- natural images
- average degree
- graph layout