Modeling pronunciation variation for spontaneous speech synthesis.

Steffen Werner Matthias Wolff Matthias Eichner Rüdiger Hoffmann

Published in: ICASSP (1) (2004)

Keyphrases

speech synthesis
speech recognition
vocal tract
text to speech
speech corpus
neural network
computer vision
expert systems
prosodic features
real world
data mining
artificial intelligence
information systems
website
case study
language model