Listening while speaking: Speech chain by deep learning.

Andros Tjandra Sakriani Sakti Satoshi Nakamura

Published in: ASRU (2017)

Keyphrases

deep learning
foreign language
synthesized speech
unsupervised learning
unsupervised feature learning
machine learning
mental models
deep architectures
weakly supervised
restricted boltzmann machine
learning algorithm
deep belief networks
data sets
feature selection
decision support system