Analysis of Stress in speech using adaptive Empirical Mode Decomposition

Author

Zhang, James Z. ; Mbitiru, Nyaga ; Tay, Peter C. ; Adams, Robert D.

Author_Institution

Dept. of Eng. & Technol., Western Carolina Univ., Cullowhee, NC, USA

fYear

2009

fDate

1-4 Nov. 2009

Firstpage

361

Lastpage

365

Abstract

Stress in human speech can be detected by various methods know as Voice Stress Analysis (VSA). The detection is accomplished by measuring the frequency shift of a microtremor normally residing in the frequency range of 8 to 12 Hz when not stressed. Conventional detection methods include Fast Fourier Transform (FFT) or McQuiston-Ford algorithm. This paper presents a new method called Adaptive Empirical Mode Decomposition (AEMD) applied to voice stress detection. Because AEMD in essence is a time-frequency analysis method, it is possible to use this method for real-time voice stress detection.

Keywords

fast Fourier transforms; speech processing; stress analysis; time-frequency analysis; McQuiston-Ford algorithm; adaptive empirical mode decomposition; conventional detection methods; fast Fourier transform; frequency 8 Hz to 12 Hz; human speech stress analysis; microtremor frequency shift; time-frequency analysis method; voice stress detection; Change detection algorithms; Delay; Fast Fourier transforms; Frequency; Human factors; Military equipment; Muscles; Psychology; Speech analysis; Stress measurement;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 2009 Conference Record of the Forty-Third Asilomar Conference on

Conference_Location

Pacific Grove, CA

ISSN

1058-6393

Print_ISBN

978-1-4244-5825-7

Type

conf

DOI

10.1109/ACSSC.2009.5469829

Filename

5469829