Robust feature extraction for mobile-based speech emotion recognition system

In this paper, we propose a robust feature extraction method for mobile-based speech emotion recognition system. A query speech signal is captured by a cellular phone in the real mobile environment. A major problem in this environment is distortions contained in the features of the query sound due to the mobile network and environmental noise. In order to alleviate these noises, a signal subspace noise reduction algorithm is applied. Then a robust feature extraction method called SFS feature optimization is implemented to improve and stabilize the system performance. The proposed system has been tested with cellular phones in the real world and it shows about 73% of average classification success rate with Fuzzy SVM classifier.

[1]  Yariv Ephraim,et al.  A signal subspace approach for speech enhancement , 1995, IEEE Trans. Speech Audio Process..

[2]  Shrikanth S. Narayanan,et al.  Classifying emotions in human-machine spoken dialogs , 2002, Proceedings. IEEE International Conference on Multimedia and Expo.

[3]  Klaus R. Scherer,et al.  Adding the affective dimension: a new look in speech analysis and synthesis , 1996, ICSLP.

[4]  Shigeo Abe,et al.  Fuzzy support vector machines for multiclass problems , 2002, ESANN.

[5]  John H. L. Hansen,et al.  Nonlinear feature based classification of speech under stress , 2001, IEEE Trans. Speech Audio Process..

[6]  Tsuyoshi Moriyama,et al.  Emotion recognition and synthesis system on speech , 1999, Proceedings IEEE International Conference on Multimedia Computing and Systems.

[7]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Frank Dellaert,et al.  Recognizing emotion in speech , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[9]  Shuichi Fukuda,et al.  Emotion in user interface, voice interaction system , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.