Considering basic emotional state information in speaker verification

Abstract

The paper presents speaker verification results for six basic emotional states. The database of emotional speech (six acted states: anger, sadness, happiness, fear, disgust, surprise) plus the neutral state were examined with a typical speaker verification system based on MFCC features and GMM classifiers. The obtained results were confronted with the subjective and objective emotion recognition scores. The significant influence of emotion on speaker recognition scores is substantially bigger for emotions with a strong activation factor.