Local-global speaker representation for target speaker extraction.
Shulin HeWei RaoKanghao ZhangYukai JuYang YangXueliang ZhangYannan WangShidong ShangPublished in: CoRR (2022)
Keyphrases
- speech recognition
- speaker verification
- speaker recognition
- audio visual
- databases
- case study
- speaker diarization
- pattern recognition
- information extraction
- automatic speech recognition
- speaker identification
- prosodic features
- real time
- acoustic features
- speech signal
- automatic extraction
- model selection
- similarity measure
- data sets