Login / Signup
Frame-level acoustic modeling based on Gaussian process regression for statistical nonparametric speech synthesis.
Tomoki Koriyama
Takashi Nose
Takao Kobayashi
Published in:
ICASSP (2013)
Keyphrases
</>
gaussian process regression
speech synthesis
prosodic features
speech recognition
gaussian processes
gaussian process
covariance function
text to speech
vocal tract
neural network
bayesian networks
multi class
generative model