This paper presents the method of detection of stress from human voice. Experimental results show that, there is a dependence of Stress on human voice. If a person is carrying Stress or feeling depressed, then it is clearly reflected from his speech. In this research for the analysis of stress (Exam-Stress) various features such as loudness, fundamental frequency, Power Spectral Density Zero-Crossing rate , etc. considered and for the decision making we are using Intelligent System .Intelligent system such as Artificial Neural Network and Adaptive Neuro-Fuzzy Interference System(ANFIS). Data base is collected form the final year student in the age group of 22 to 24 , before and after final viva-examination of University Examination .For this word is choosing “ I am fine, How are you ? “

1. G. Fink, Encyclopedia of Stress. London, New York: Academic Press, 2007
2. M. Sigmund, “Introducing the database Exam Stress for speech under stress,” Proceedings of 7th IEEE Nordic Signal Processing Symposium (NORSIG 2006). Reykjavik, pp. 290-293, 2006.
3. O. Lippold, “Physiological Microtremor,” Scientific American, 224(3): pg. 65-73. 1971
4. T. Shipp M. Brenner. Voice stress analysis: Mental state estimation. In J.R. Cons truck, editor, NASA conf. pub. 2504, 1987.
5. ‘Analysis of Stress in Speech Using Empirical Mode Decomposition’ by Nyaga Mbitiru, Peter Tay, James Z. Zhang, Robert D. Adams.
6. ‘Voice Stress Extraction’ by Gra¿yna Demenko ,Institute of Linguistic Adam , Mickiewicz University, Poznañ.
7. Digital Signal Processing of Speech Signal By : Schefar
8. “Neuro Fuzzy and Soft computing”, Jang, Sun, Mezutani
9. Analysis of Fundamental Frequency Contours in Speech, H. Levitt and L. R. Rabiner, Journ.Acoust. Soc. Amer., Vol. 49, No. 2, pp. 569-582, February 1971.

Speech Exam-Stress Spectral Analysis Fuzzy-Logic