Improving the Understandability of Speech Synthesis by Modeling Speech in Noise.

Brian Langner Alan W. Black

Published in: ICASSP (1) (2005)

Keyphrases

speech synthesis
speech recognition
text to speech
vocal tract
prosodic features
noisy environments
speech corpus
speech enhancement
noisy data
speech signal
random noise
noise reduction
hidden markov models
noise model
data sets
audio visual
subband
bayesian networks
image processing