Sign in
Accurate Visible Speech Synthesis Based on Concatenating Variable Length Motion Capture Data.
Jiyong Ma
Ronald A. Cole
Bryan L. Pellom
Wayne H. Ward
Barbara Wise
Published in:
IEEE Trans. Vis. Comput. Graph. (2006)
Keyphrases
</>
variable length
speech synthesis
human motion
motion capture data
fixed length
speech recognition
motion capture
n gram
text to speech
bitstream
human body
video sequences
high quality
pattern recognition
image sequences
human actions
action recognition
text classification