PERFORMANCE OPTIMIZATION on EMOTION RECOGNITION from SPEECH

Abstract

This work presents MFCC-based emotion recognition from speech. For this purpose; after features of labeled speech signals are extracted and a classifier is trained, the classification performance is measured over test data. Contribution of each parameter to the classification performance is exhibited by training the system with different parameters. Additionally; the role of MFCC features in emotion recognition is analyzed by comparing the results to others obtained with additional features.