Quantized HMMs for low footprint text-to-speech synthesis.

Alexander Gutkin Xavi Gonzalvo Stefan Breuer Paul Taylor

Published in: INTERSPEECH (2010)

Keyphrases

text to speech synthesis
hidden markov models
speech recognition
data sets
real world
decision trees
pattern recognition
high levels
dct coefficients
text to speech
database
image processing
computational complexity
viterbi algorithm