Login / Signup
Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis.
Heiga Zen
Andrew W. Senior
Published in:
ICASSP (2014)
Keyphrases
</>
speech synthesis
prosodic features
speech recognition
text to speech
social networks
statistical modeling
vocal tract
mixture model
kernel density estimators
neural network
hidden markov models
speech signal
heterogeneous networks