Speaker-adaptive visual speech synthesis in the HMM-framework.

Dietmar Schabus Michael Pucher Gregor Hofer

Published in: INTERSPEECH (2012)

Keyphrases

speech recognition
speech synthesis
hidden markov models
main contribution
vocal tract
real time
multimedia
speech signal
neural network
low level
probabilistic model
lightweight
visual information
automatic speech recognition
speaker identification
text to speech