期刊名称：International Journal of Electrical, Electronics and Computer Engineering
电子版ISSN：2277-2626
出版年度：2013
期号：829
页码：7
出版社：RESEARCH TREND
摘要：ABSTRACT: Studies have shown that distortion introduced by stress or emotion can severely reduce speech recognition accuracy. Techniques for detecting or assessing the presence of stress could help neutralize stressed speech and improve robustness of speech recognition systems. The performance of a speaker recognition system decreases when the speaker is under stress or emotion. In this dissertation we explore and identify a mechanism that enables use of inherent stress-in-speech or speaking style information present in speech of a person as additional cues for speaker recognition. Stress in human speech can be detected by various methods know as Voice Stress Analysis (VSA).Stress detection in voice gives a great alternative for obtaining a noninvasive way to extract information about a possible deception from a person declaration. This article contains information and results of a primary work done to show how changes the stress For Mel Frequency Cepstral Coefficient features can be detected through FFT signal processing when a person is under psychological pressure. The principal purpose is to obtain a tool that could help innocent people to prove their guiltlessness of having committed an offense or a crime
