Support vector machines employing cross-correlation for emotional speech recognition

Emotional speech classification is a current area of research with wide variety of applications in intelligent human–machine interaction systems. For classifying emotional speech signals, it is quite common to use either statistical features or temporal features. This paper proposes a relatively new cross-correlation based feature extractor and is aided with support vector machine classifier for emotional speech recognition. In this paper the proposed technique has been utilized for classification of four kinds of emotional speech signals. The support vector machine classifier employs suitable features extracted from crosscorrelograms of emotional speech signals. This cross-correlation aided SVM classification system could achieve an overall classification accuracy as high as 84.55%. The results also divulge that the SVM classifier detects anger emotion efficiently with a recognition rate of 95.04%.