Audio-visual based emotion recognition using tripled hidden Markov model.

Mingli Song Chun Chen Mingyu You

Published in: ICASSP (5) (2004)

Keyphrases

audio visual
hidden markov models
emotion recognition
multi stream
multimodal fusion
multi modal
affective states
visual information
visual data
gesture recognition
speech recognition
temporal context
multimedia
facial expressions
search engine
spatio temporal
image classification
co occurrence
audio features