Paper Info
Title
Audio-visual based emotion recognition using tripled hidden Markov model
Abstract
Emotion recognition is one of the latest challenges in intelligent human/machine communication. Most of previous work on emotion recognition focused on extracting emotions from visual or audio information separately. A novel approach is presented in this paper to recognize the human emotion which uses both visual and audio from video clips. A tripled hidden Markov model is introduced to perform the recognition which allows the state asynchrony of the audio and visual observation sequences while preserving their natural correlation over time. The experimental results show that this approach outperforms only using visual or audio separately.
Year
DOI
Venue
2004
10.1109/ICASSP.2004.1327251
ICASSP (5)
Keywords
Field
DocType
video signal processing,video clip audio,man-machine systems,face recognition,speech recognition,maximum likelihood estimation,intelligent human/machine communication,audio-visual based emotion recognition,emotion recognition,feature extraction,audio/visual time correlation,visual feature extraction,audio/visual state asynchrony,human emotion,tripled hidden markov model,viterbi algorithm,hidden markov models,correlation methods,hidden markov model,shape
Visual observation,Facial recognition system,Asynchrony,Pattern recognition,Emotion recognition,Computer science,Audio mining,Speech recognition,Feature extraction,Artificial intelligence,Hidden Markov model,Viterbi algorithm
Conference
Volume
ISSN
ISBN
5
1520-6149
0-7803-8484-9
Citations 
PageRank 
References 
13
0.78
7
Authors
3
Name
Order
Citations
PageRank
Mingli Song1164698.10
Chun Chen24727246.28
Mingyu You316016.22