Annotation: This paper presents a voice identification method based on machine learning. The general algorithm of voice identification is considered. The results of the analysis of common solutions in the area of voice identification are presented. The use of cepstral transformations and deep learning methods for convolutional neural networks is proposed. A software prototype has been developed and the results of its testing have been presented. The results of evaluating the effectiveness of the developed method are presented.

Keywords: biometric identification, classification, machine learning, neural network, algorithm, MFCC, CNN