Login / Signup
Comprehensive many-to-many phoneme-to-viseme mapping and its application for concatenative visual speech synthesis.
Wesley Mattheyses
Lukas Latacz
Werner Verhelst
Published in:
Speech Commun. (2013)
Keyphrases
</>
speech synthesis
visual speech
text to speech
speech recognition
hidden markov models
speech corpus
prosodic features
speaker identification
vocal tract
speech signal
noisy environments
automatic speech recognition
visual information
visual features
low level
information retrieval
neural network