Speech emotion recognition using multiple discriminant analysis and gaussian mixture model

Abstract

In this paper we studied speech emotion recognition from Mandarin speech signal. Five basic emotion classes and the neutral state are considered. In a listening experiment we verified the speech corpus using a judgment matrix. Acoustic parameters including short-term energy, pitch contour, and formants are extracted from emotional speech signal. Gaussian mixture model is then adopted for training the emotion model. Due to the data challenge in GMM training, we use multiple discriminant analysis for feature optimization and compared with basic Fisher discriminant ratio based method. The experimental results show that using multiple discriminant analysis our GMM classifier gives a promising recognition rate for Mandarin speech emotion recognition.