Detection of stress and emotion in speech using traditional and FFT based log energy features

In this paper, a novel system for detection of human stress and emotion in speech is proposed. The system makes use of FFT based linear short time log frequency power coefficients (LFPC) and TEO based nonlinear LFPC features in both time and frequency domains. 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.