Speech emotion recognition using RBF kernel of LIBSVM

Automatic Speech Emotion Recognition (SER) is a current research topic in the field of Human Computer Interaction (HCI) with wide range of applications. The speech features such as, Mel Frequency cepstrum coefficients (MFCC) and Mel Energy Spectrum Dynamic Coefficients (MEDC) are extracted from speech utterance. The LIBSVM is used as classifier to identify different emotional states such as anger, happiness, sadness, neutral, fear, from Berlin emotional database. The results are taken by using RBF kernel of LIBSVM. It gives 93.75% recognition accuracy for RBF kernel.