Hierarchical Speaker Representation for Target Speaker Extraction.
Shulin HeHuaiwen ZhangWei RaoKanghao ZhangYukai JuYang YangXueliang ZhangPublished in: ICASSP (2024)
Keyphrases
- speaker verification
- speech recognition
- speaker recognition
- audio visual
- automatic speech recognition
- hierarchical representation
- information extraction
- speaker identification
- data sets
- automatic extraction
- hierarchically structured
- representation scheme
- speaker diarization
- maximum likelihood
- hierarchical organization
- hierarchical reinforcement learning
- synthesized speech
- hierarchical model
- coarse to fine
- multi modal