Humanoid Audio-Visual Avatar With Emotive Text-to-Speech Synthesis.

Hao Tang Yun Fu Jilin Tu Mark Hasegawa-Johnson Thomas S. Huang

Published in: IEEE Trans. Multim. (2008)

Keyphrases

audio visual
text to speech synthesis
multi modal
humanoid robot
text to speech
visual information
human computer interaction
multimedia
visual data
emotion recognition
video summarization
temporal context
multi stream
person authentication
multimodal fusion
audio visual speech recognition
data sets
video retrieval