Browse > Article
http://dx.doi.org/10.5302/J.ICROS.2006.12.7.666

Reinforcement Learning Method Based Interactive Feature Selection(IFS) Method for Emotion Recognition  

Park Chang-Hyun (중앙대학교)
Sim Kwee-Bo (중앙대학교)
Publication Information
Journal of Institute of Control, Robotics and Systems / v.12, no.7, 2006 , pp. 666-670 More about this Journal
Abstract
This paper presents the novel feature selection method for Emotion Recognition, which may include a lot of original features. Specially, the emotion recognition in this paper treated speech signal with emotion. The feature selection has some benefits on the pattern recognition performance and 'the curse of dimension'. Thus, We implemented a simulator called 'IFS' and those result was applied to a emotion recognition system(ERS), which was also implemented for this research. Our novel feature selection method was basically affected by Reinforcement Learning and since it needs responses from human user, it is called 'Interactive feature Selection'. From performing the IFS, we could get 3 best features and applied to ERS. Comparing those results with randomly selected feature set, The 3 best features were better than the randomly selected feature set.
Keywords
reinforcement learning; feature selection; emotion recognition; speech signal;
Citations & Related Records
연도 인용수 순위
  • Reference
1 C. H. Park and K. B Sim, 'The implementation of the emotion recognition from speech and facial expression system,' Proc. of ICNC'05-FSKD'05, pp. 85-88, Aug. 27-29, 2005
2 D. Ververidis and C. Kotropoulos, 'Emotional speech classification using Gaussian mixture models,' Proceedings of ISCAS, vol. 3, pp. 2871-2874, May, 2005   DOI
3 C. M. Lee and S. S Narayanan, 'Toward detecting emotions in spoken dialogs,' IEEE Transactions on Speech and Audio Processing, vol. 13, pp. 293-303, March, 2005   DOI   ScienceOn
4 J. Wagner, J. H. Kim, and E. Andre, 'From physiological signals to emotions: Implementing and comparing selected methods for feature extraction and classification,' Proceedings of ICME, pp. 940-943, July, 2005
5 P. Pudil and J. Novovicova, 'Novel methods for subset selection with respect to problem knowledge,' IEEE Intelligent Systems, pp. 66-74, March, 1998   DOI   ScienceOn
6 Y. L. Lin and W. Gang, 'Speech emotion recognition based on HMM and SYM,' Proceedings of Machine Learning and Cybernetics, vol. 8, pp. 4898-4901, Aug. 2005
7 F. Morchen, A. Ultsch, M. Thies, and I. Lohken, 'Modeling timbre distance with temporal statistics from polyphonic music,' IEEE transaction on Audio,Speech and Language Processing, vol. 14, Issue 1, pp. 81-90, Jan. 2006   DOI   ScienceOn
8 E. F. Combarro, E. Montanes, I. Diaz, J. Ranilla, and R Mones, 'Introducing a family of linear measures for feature selection in text categorization,' IEEE transactions on Knowledge and Data Engineeringl, vol. 17, no. 9, pp. 1223-1232, Sept. 2005   DOI   ScienceOn
9 R. S. Sutton and A. G. Barto, Reinforcement Learning :An Introduction, A bradford book, London, 1998