MC-SpEx: Towards Effective Speaker Extraction with Multi-Scale Interfusion and Conditional Speaker Modulation.
Jun ChenWei RaoZilin WangJiuxin LinYukai JuShulin HeYannan WangZhiyong WuPublished in: CoRR (2023)
Keyphrases
- multiscale
- speech recognition
- speaker verification
- speaker recognition
- audio visual
- automatic speech recognition
- prosodic features
- scale space
- speaker identification
- coarse to fine
- random field model
- speech synthesis
- data sets
- resource allocation
- information extraction
- hidden markov models
- image segmentation
- case study