No Access

SPEECH EMOTION RECOGNITION METHOD BASED ON IMPROVED DECISION TREE AND LAYERED FEATURE SELECTION

QIRONG MAO

Department of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China

Search for more papers by this author

XIAOJIA WANG

Department of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China

Search for more papers by this author

, and

YONGZHAO ZHAN

Department of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China

Search for more papers by this author

https://doi.org/10.1142/S0219843610002088Cited by:15 (Source: Crossref)

Abstract

In this paper, in order to improve the classification accuracy with features as few as possible, a new hierarchical recognition method based on an improved SVM decision tree and the layered feature selection method combining neural network with genetic algorithm are proposed. The improved SVM decision tree is constructed according to confusion degrees between two emotions or those between two emotion groups. The classifier in each node of the improved decision tree is a SVM. On the emotional speech corpus recorded by our workgroup including 7 emotions, with the features and parameters gotten by the method combining neural network with genetic algorithm, improved SVM decision tree, multi-SVM, SVM-based binary decision tree, the traditional SVM-based decision directed acyclic graph and HMM are evaluated respectively. The experiments reveal that, compared with the other four methods, the proposed method in this paper appears better classification accuracy with fewer features and less time.

Keywords:

References

M. W. Bhatti, Y. Wang and L. Guan, A neural network approach for human emotion recognition in speech, IEEE Int. Conf. Symposium on Circuits and Systems (ISCAS) (IEEE Press, Vancouver, BC, Canada, 2004) pp. 181–184. Google Scholar
T. L. Nwe, S. W. Foo and L. C. D. Silva, Speech Communication 41(4), 603 (2003), DOI: 10.1016/S0167-6393(03)00099-2. Crossref, Web of Science, Google Scholar
B. Schuller, G. Rigoll and M. Lang, Hidden Markov model-Based speech emotion recognition, IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP) (IEEE Press, New York, USA, 2003) pp. 1–4. Google Scholar
M. H. Moataz, S. Mohamed and K. Fakhri, Speech emotion recognition using gaussian mixture Vector autoregressive models, IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP) (IEEE Press, Beijing, China, 2007) pp. IV-957–IV-960. Google Scholar
H. Hu, M. X. Xu and W. Wu, GMM supervector based SVM with spectral features for speech emotion recognition, IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP) (IEEE Press, Beijing, China, 2007) pp. 413–416. Google Scholar
Y. J. Wang and L. Guan, IEEE Transactions on Multimedia 10(4), 659 (2008), DOI: 10.1109/TMM.2008.921734. Crossref, Web of Science, Google Scholar
Z. H. Zenget al., IEEE Transactions on Multimedia 10(4), 570 (2008), DOI: 10.1109/TMM.2008.921737. Crossref, Web of Science, Google Scholar
Y. L. Lin, G. Wei and K. C. Yang, Journal of Circuits and Systems 12(1), 90 (2007). Web of Science, Google Scholar
V. Dimitrios and K. Constantine, Speech Communication 48, 1162 (2006). Web of Science, Google Scholar
D. N. Jiang and L. H. Cai, Speech Emotion Classification with the Combination of Statistic Features and Temporal Features, IEEE Int. Conference on Multimedia and Expo (ICME) (IEEE Press, Taipei, Taiwan, 2004) pp. 1967–1970. Google Scholar
O. W. Kwonet al., Emotion recognition by speech signals, Proceedings of Euro Speech (Geneva, Switzerland, 2003) pp. 125–128. Google Scholar
N. Tetsuya et al. , Adaptive emotion recognition in speech by feature selection based on KL-divergence , IEEE Int. Conference on Systems, Man, and Cybernetics ( IEEE Press , Taipei, Taiwan , 2006 ) . Google Scholar
X. J. Wang , Q. R. Mao and Y. Z. Zhan , Speech emotion feature selection method based on contribution analysis algorithm of neural network , IEEE Int. Conf. on Sensing Technology ( IEEE press , Palmerston North, New Zealand , 2007 ) . Google Scholar
C. H. Huang and C. J. Wang, Expert Systems with Applications 31(2), 231 (2006), DOI: 10.1016/j.eswa.2005.09.024. Crossref, Web of Science, Google Scholar
C. Roddy and R. C. Randolph, Speech Communication 40, 5 (2003). Web of Science, Google Scholar
L. Zhaoet al., Journal of Communication 21(10), 18 (2000). Web of Science, Google Scholar
Y. Z. Zhan and P. Cao, Research and implementation of emotional feature extraction and recognition in speech signal, Journal of Jiangsu University (National Science Edition), 26(1) (2005) 72–75. (in Chinese) . Google Scholar
Y. L. Lin, Research on Speech Emotion Recognition. PhD Thesis. (South China University of Technology, Guangzhou, China, 2006), pp. 51–57. (in Chinese) . Google Scholar