Analysis of Speech under Stress based on Short-Time Spectrum of Vowel Phonemes

M. Sigmund and Z. Brabec (Czech Republic)

Keywords

Speech signal, spectral analysis, stress detection.

Abstract

This paper deals with speech signal spoken by speaker under psychological stress. The investigation of speaker’s stress is based on specific changes in short-time spectrum of vowel phonemes. For each selected signal segment, the spectrum was computed by means of two different approaches: Fourier transform and chirp transform. Comparative results between both spectra served for speaker’s stress identification. In case of speech under stress, the obtained spectra differ towards the higher frequencies due to enhanced pitch modulation observed in the envelope of the chirp spectrum. For use in our experiments, a new database of speech under stress consisting of data collected during oral examinations at our university was created.

Important Links:



Go Back


IASTED
Rotating Call For Paper Image