Login / Signup
Tying covariance matrices to reduce the footprint of HMM-based speech synthesis systems.
Keiichiro Oura
Heiga Zen
Yoshihiko Nankaku
Akinobu Lee
Keiichi Tokuda
Published in:
INTERSPEECH (2009)
Keyphrases
</>
covariance matrices
speech synthesis
covariance matrix
hidden markov models
maximum likelihood
speech recognition
computer vision
gaussian mixture model
text to speech
high dimensional
prior knowledge
vector space