An immunological model of clonal selection with positive selection based on the principles of mass-parallel data processing used in artificial immune systems, is proposed. The model is designed for text-independent identification of a person by voice. In contrast to known passwordbased voice identification systems, the proposed model implements decentralized recognition of voice data by matching it with detectors that simulate immunocompetent cells of the immune system. The initial voice features are generated in a linear speech predictor and are represented by cepstral coefficients. The sequence of cepstral coefficients is further divided into equal time sections - morphemes, which are abstract linguistic units that unify phonemes. Morphemes carry the individual coloring of consecutive temporal segments of speech reproduced by the voice, allowingthem to be used productively as voice identifiers. The matching of voice morphemes with detectors is carried out according to the principle of positive selection based on the Euclidean proximity measure. The model's "friend-or-foe" identification decision making is implemented on the basis of a statistical approach in terms of the frequency of detector response. The proposed model implements the identification of the speaker's personality at the rate of receipt of his voice data. At the same time, personality identification is invariant to the language, volume and content of speech. The advantage of the model is complete protection against replay attacks. The effective realization of the model, the accuracy and speed of identification are due to the possibility of organizing highspeed analysis of large volumes of voice data, which in the long term corresponds to the pace of development and application of high-performance computing systems.
