Speech emotion recognition based on rough set and SVM

Speech emotion recognition is becoming more and more important in such computer application fields as health care, children education, etc. There are a few works have been done on speech emotion recognition using such methods as ANN, SVM, etc in the last years. Traditional feature selection method used in speech emotion recognition is computationally too expensive to determine an optimum or suboptimum feature subset. In this paper, a novel approach based on rough set theory and SVM for speech emotion recognition is proposed. The experiment results show this approach can reduce the calculation cost while keeping high recognition rate.