Automatic Speech Emotion Recognition using Support Vector Machine

Automatic Speech Emotion Recognition (SER) is a current research topic in the field of Human Computer Interaction (HCI) with wide range of applications. The purpose of speech emotion recognition system is to automatically classify speaker's utterances into five emotional states such as disgust, boredom, sadness, neutral, and happiness. The speech samples are from Berlin emotional database and the features extracted from these utterances are energy, pitch, linear prediction cepstrum coefficients (LPCC), Mel Frequency cepstrum coefficients (MFCC), Linear Prediction coefficients and Mel cepstrum coefficients (LPCMCC). The Support Vector Machine (SVM) is used as a classifier to classify different emotional states. The system gives 66.02% classification accuracy for only using energy and pitch features, 70.7% for only using LPCMCC features, and 82.5% for using both of them.