Efficient Speech Emotion Recognition Based on Multisurface Proximal Support Vector Machine

An efficient speech emotion recognition method based on Multisurface Proximal Support Vector Machine (MPSVM) is presented in this paper. Seven primary human emotions including anger, boredom, disgust, fear/anxiety, happiness, neutral, sadness are investigated using cepstral and spectral features. These novel and robust acoustic features and the multisurface proximal support vector machine classifier based on the Gaussian Mixture Models (GMM) are proposed to yield more correct result. In order to get the normal features in speech emotion space, the corpus of Berlin database of emotional speech is used to train the system, and a simple speech emotion corpus in English, French, Slovenian and Spanish recorded by 2 non-professional speakers are used to test the classifiers. The results achieved by MPSVM are compared by that of the standard support vector machine (SSVM) classifier. The more efficient and more accurate results are achieved.