Multi-View Self-Attention Based Transformer for Speaker Recognition.

Rui Wang Junyi Ao Long Zhou Shujie Liu Zhihua Wei Tom Ko Qing Li Yu Zhang

Published in: CoRR (2021)

Keyphrases

multi view
speaker recognition
single view
gaussian mixture model
multiple views
vector quantization
d objects
speaker verification
speaker identification
probabilistic neural network
semi supervised
training data
multi view learning
three dimensional
speech recognition
viewpoint
pattern recognition