Voice Biometric System for Speaker Authentication
Thomas, Sachdevp. Raut, D. Srivastava N. Shah · 2015
This paper discusses the implementation of a textindependent, biometric, Speaker Recognition based security system. Such a bio-metric model can be used to identify a person based on his or her voice-print. Mel Frequency Cepstral Coefficients (MFCCs) are used to denote the unique features of a person‟s speech and Vector Quantization has been used to generate speaker specific codebooks.The traditional techniques of speech processing like end-point detection, pre-emphasis, windowing, Fourier transformation have been used. The advantages and limitations of the proposed system are also stated in this paper.