Multi-View Self-Attention Based Transformer for Speaker Recognition.
Rui WangJunyi AoLong ZhouShujie LiuZhihua WeiTom KoQing LiYu ZhangPublished in: ICASSP (2022)
Keyphrases
- multi view
- speaker recognition
- gaussian mixture model
- single view
- multiple views
- speaker verification
- vector quantization
- d objects
- three dimensional
- speaker identification
- probabilistic neural network
- speech recognition
- semi supervised
- multi view learning
- speech signal
- unsupervised learning
- hidden markov models
- viewpoint
- face recognition