COMPARISON BETWEEN GMM-SVM SEQUENCE KERNEL AND GMM: APPLICATION TO SPEECH EMOTION RECOGNITION

Speech emotion recognition aims at automatically identifying the emotional or physical state of a human being from his or her voice. The emotional state is an important factor in human communication, because it provides feedback information in many applications. This paper makes a comparison of two standard methods used for speaker recognition and verification: Gaussian Mixture Models (GMM) and Support Vector Machines (SVM) for emotion recognition. An extensive comparison of two methods: GMM and GMM/SVM sequence kernel is conducted. The main goal here is to analyze and compare influence of initial setting of parameters such as number of mixture components, used number of iterations and volume of training data for these two methods. Experimental studies are performed over the Berlin Emotional Database, expressing different emotions, in German language. The emotions used in this study are anger, fear, joy, boredom, neutral, disgust, and sadness. Experimental results show the effectiveness of the combination of GMM and SVM in order to classify sound data sequences when compared to systems based on GMM.