Estimating the Closeness of Known and Unknown Speech Signal Using MATLAB

In todays world implementation of any expert system with maximum data and networking security becomes a real necessity in academic organizations as well as industrial communities. In this paper, an expert security system is developed using speech recognition technology. A human can easily recognize a familiar voice however; getting a computer to distinguish a particular voice among others is a more difficult task. This paper describes the process behind implementing a speaker recognition algorithm in MATLAB. The algorithm utilizes the Discrete Fourier Transform in order to compare the frequency spectra of two voices. A plot is then generated depicting how the normalized frequency spectra in your voice and compare to the average normal vector of voice data. The algorithm makes a comparison and displays in the command window YOU ARE NOT!!!! if you do not fall within 2 standard deviation of the normal average voice. If you do happen to fall within 2 standard deviation, then the command window displays HELLO!!!