Sign in
Training combination strategy of multi-stream fused hidden Markov model for audio-visual affect recognition.
Zhihong Zeng
Yuxiao Hu
Ming Liu
Yun Fu
Thomas S. Huang
Published in:
ACM Multimedia (2006)
Keyphrases
</>
multi stream
hidden markov models
audio visual
audio visual speech recognition
multi modal
visual information
training set
speech recognition
affective states
multimedia
emotion recognition
visual data
feature extraction
gesture recognition
activity recognition
context aware
audio features
machine learning