Abstract

Abstract: - Recognizing the emotions from the speech is essential for a natural connection between man and machine. In speech emotion recognition, emotional state of a speaker is extracted from his or her speech. A speech emotion recognition system is made to detect the emotion through the audio speech signals. The efficiency of emotion recognition system depends on type of features extracted and classifier used for detection of emotions. In this paper we have taken the audio features of MFCC, MEL, and Chroma. to recognize the emotion of speaker like sad, neutral, happy, angry. With the model proposed of MLP classifier we have achieved accuracy of 78% approximately.Keywords: - MLP Classifier, MFCC, Chroma, MEL.