Login / Signup
A structured speech model with continuous hidden dynamics and prediction-residual training for tracking vocal tract resonances.
Li Deng
Leo J. Lee
Hagai Attias
Alex Acero
Published in:
ICASSP (1) (2004)
Keyphrases
</>
prediction model
probabilistic model
parameter estimation
vocal tract
random fields
computer vision
image acquisition
speech signal
noisy environments
speech synthesis