Login / Signup
TD-PSOLA versus harmonic plus noise model in diphone based speech synthesis.
Ann K. Syrdal
Yannis Stylianou
Laurie Garrison
Alistair Conkie
Jürgen Schröter
Published in:
ICASSP (1998)
Keyphrases
</>
noise model
speech synthesis
speech recognition
text to speech
noise level
noisy images
gaussian distribution
vocal tract
optimization procedure
learning algorithm
parameter space
gaussian noise
noise reduction
error rate
automatic speech recognition
graph cuts
hidden markov models
reinforcement learning