Analysis and detection of human emotion and stress from speech signals

Abstract

In this thesis, a novel system of stress and emotion classification in speech is proposed. The system makes use of linear short time Log Frequency Power Coefficients (LFPC) and TEO based nonlinear LFPC features in both time and frequency domain. The performance of the proposed system is compared with the traditional approaches which use features of LPCC and MFCC. The comparison of each approach is performed using SUSAS (Speech Under Simulated and Actual Stress) and ESMBS (Emotional Speech of Mandarin and Burmese Speakers) databases. It is observed that proposed system outperforms the traditional systems. Results show that, the system using LFPC gives the highest accuracy (87.8% for stress, 89.2% for emotion classification) followed by the system using NFD-LFPC feature. While the system using NTD-LFPC feature gives the lowest accuracy. Experimental results also show that the performance of the proposed system does not degrade drastically with increase in noise.