Voice Biometric System

The paper presents an economic solution that may be used in speaker authentication applications or in biomedical waveform diagnostics (EEG, ECG). The usual approaches require important computational resources generally employing complex signal processing methods in the frequency domain. This work proposes a low-complexity/low-cost implementation of the TESPAR (Time Encoded Signal Processing and Recognition) coding method on an ATMEL microcontroller platform. The computational requirements for this method are two orders of magnitude less than that required by other usual methods. The performed experiments studied the variation of the TESPAR-S matrices as a function of the password utterance manner: exclaiming, interrogative, slow, fast and normal and as function of the password type: a common password for all enrolled speakers and different passwords. The best results were provided in the case of cooperating utterances, when the speed of uttering the password was normal.