Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding.

Hongning Zhu Kong Aik Lee Haizhou Li

Published in: Interspeech (2021)

Keyphrases

multi layer
neural network
feed forward neural networks
error back propagation
network architecture
neural nets
single layer
speech recognition
focus of attention
feature selection
object recognition
high dimensional
visual attention
group sparse coding