A Deep Learning Approach to Data-driven Parameterizations for Statistical Parametric Speech Synthesis.

Prasanna Kumar Muthukumar Alan W. Black

Published in: CoRR (2014)

Keyphrases

data driven
deep learning
speech synthesis
speech recognition
text to speech
unsupervised learning
unsupervised feature learning
vocal tract
machine learning
weakly supervised
mental models
deep architectures
hidden markov models
neural network
domain specific
text mining
image processing