Design of an audio-visual speech corpus for the czech audio-visual speech synthesis.

Milos Zelezný Petr Císar Zdenek Krnoul Jan Novák

Published in: INTERSPEECH (2002)

Keyphrases

audio visual
speech synthesis
speech corpus
multi modal
visual information
speech recognition
multi stream
visual data
multimedia
audio visual speech recognition
emotion recognition
text to speech
pattern recognition
non stationary
video sequences
feature extraction
high level
feature selection
data sets