The ByteDance Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2021.
Keke WangXudong MaoHao WuChen DingChuxiang ShangRui XiaYuxuan WangPublished in: CoRR (2021)
Keyphrases
- speaker recognition
- speaker diarization
- speaker verification
- speaker identification
- speech recognition
- gaussian mixture model
- vector quantization
- speech signal
- probabilistic neural network
- noisy environments
- language identification
- broadcast news
- emotion recognition
- bayesian information criterion
- acoustic features
- audio visual
- generative model
- maximum likelihood
- feature extraction
- language model
- hidden markov models
- feature vectors
- feature space