Security System Aided by Voice Fingerprint

Abstract The goal of this paper is to create a security system to identify a specific person who wants to access private information or enter a building using their voice. To perform this system, we identified a database containing the audio files of the users who will be able to authenticate with this system. Several steps were sequentially performed in order to extract the characteristics of the Mel Frequency Cepstral Coefficients from the audio files. Based on the k-Nearest Neighbor algorithm with an Euclidean distance and 4 neighbors, a training model was created. Through experimental results we prove in two ways, using confusion matrix and scatter plot, that the overall voice fingerprint recognition is 100%, for this particular configuration.