Abstract
This chapter introduces the current data fusion strategies among audiovisual signals for bimodal emotion recognition. Face detection, in the chapter, is performed based on the adaboost cascade face detector and can be used to provide initial facial position and reduce the time for error convergence in feature extraction. In the chapter, active appearance model (AAM) is employed to extract the 68 labeled facial feature points (FPs) from 5 facial regions including eyebrow, eye, nose, mouth, and facial contours for later facial animation parameters (FAPs) calculation. Three kinds of primary prosodic features are adopted, including pitch, energy, and formants F1-F5 in each speech frame for emotion recognition. Finally, a semi-coupled hidden Markov model (SC-HMM) is proposed for emotion recognition based on state-based alignment strategy for audiovisual bimodal features.
| Original language | English |
|---|---|
| Title of host publication | Emotion Recognition |
| Subtitle of host publication | A Pattern Analysis Approach |
| Publisher | wiley |
| Pages | 493-513 |
| Number of pages | 21 |
| ISBN (Electronic) | 9781118910566 |
| ISBN (Print) | 9781118130667 |
| DOIs | |
| Publication status | Published - 2015 Jan 2 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Engineering(all)
- Computer Science(all)
Cite this
}
Audiovisual Emotion Recognition Using Semi-Coupled Hidden Markov Model with State-Based Alignment Strategy. / Wu, Chung-Hsien; Lin, Jen Chun; Wei, Wen Li.
Emotion Recognition: A Pattern Analysis Approach. wiley, 2015. p. 493-513.Research output: Chapter in Book/Report/Conference proceeding › Chapter
TY - CHAP
T1 - Audiovisual Emotion Recognition Using Semi-Coupled Hidden Markov Model with State-Based Alignment Strategy
AU - Wu, Chung-Hsien
AU - Lin, Jen Chun
AU - Wei, Wen Li
PY - 2015/1/2
Y1 - 2015/1/2
N2 - This chapter introduces the current data fusion strategies among audiovisual signals for bimodal emotion recognition. Face detection, in the chapter, is performed based on the adaboost cascade face detector and can be used to provide initial facial position and reduce the time for error convergence in feature extraction. In the chapter, active appearance model (AAM) is employed to extract the 68 labeled facial feature points (FPs) from 5 facial regions including eyebrow, eye, nose, mouth, and facial contours for later facial animation parameters (FAPs) calculation. Three kinds of primary prosodic features are adopted, including pitch, energy, and formants F1-F5 in each speech frame for emotion recognition. Finally, a semi-coupled hidden Markov model (SC-HMM) is proposed for emotion recognition based on state-based alignment strategy for audiovisual bimodal features.
AB - This chapter introduces the current data fusion strategies among audiovisual signals for bimodal emotion recognition. Face detection, in the chapter, is performed based on the adaboost cascade face detector and can be used to provide initial facial position and reduce the time for error convergence in feature extraction. In the chapter, active appearance model (AAM) is employed to extract the 68 labeled facial feature points (FPs) from 5 facial regions including eyebrow, eye, nose, mouth, and facial contours for later facial animation parameters (FAPs) calculation. Three kinds of primary prosodic features are adopted, including pitch, energy, and formants F1-F5 in each speech frame for emotion recognition. Finally, a semi-coupled hidden Markov model (SC-HMM) is proposed for emotion recognition based on state-based alignment strategy for audiovisual bimodal features.
UR - http://www.scopus.com/inward/record.url?scp=85016374157&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85016374157&partnerID=8YFLogxK
U2 - 10.1002/9781118910566.ch19
DO - 10.1002/9781118910566.ch19
M3 - Chapter
SN - 9781118130667
SP - 493
EP - 513
BT - Emotion Recognition
PB - wiley
ER -