Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?
Sanyuan ChenYu WuChengyi WangShujie LiuZhuo ChenPeidong WangGang LiuJinyu LiJian WuXiangzhan YuFuru WeiPublished in: CoRR (2022)
Keyphrases
- speech recognition
- speaker recognition
- speaker identification
- speech signal
- vector quantization
- gaussian mixture model
- pattern recognition
- hidden markov models
- probabilistic neural network
- speech recognizer
- information retrieval
- noisy environments
- speaker verification
- pattern classification
- speech recognition systems
- language model
- supervised learning
- multimedia