A New Human Voice Recognition System

Abstract

In an effort to provide a more efficient representation of the speech signal, the application of the wavelet analysis is considered. This research presents an effective and robust method for extracting features for speech processing. Here, we proposed a new human voice recognition system using the combination of decimated wavelet (DW) and Relative Spectra Algorithm with Linear Predictive coding. First, we will apply the proposed techniques to the training speech signals and then form a train feature vector which contains the low level features extracted, wavelet and linear predictive coefficients. Afterwards, the same process will be applied to the testing speech signals and will form a test feature vector. Now, we will compare the two feature vectors by calculating the Euclidean distance between the vectors to identify the speech and speaker. If the distance between two vectors is near to zero then the tested speech/speaker will be matched with the trained speech/speaker. Simulation results have been compared with LPC scheme, and shown that the proposed scheme has performed superior to the existing technique by using the fifty preloaded voice signals from six individuals, the verification tests have been carried and an accuracy rate of approximately 90 % has been achieved.