Discriminative speaker embedding with serialized multi-layer multi-head attention.

Hongning Zhu Kong Aik Lee Haizhou Li

Published in: Speech Commun. (2022)

Keyphrases

multi layer
neural network
neural nets
error back propagation
feed forward neural networks
head pose estimation
object recognition
semi supervised
unsupervised learning
speech recognition
group sparse coding
single layer
latent space
computational intelligence
multiscale
decision trees
machine learning