IMMUNOLOGICAL METHOD OF TEXT-INDEPENDENT VERIFICATION OF PERSONALITY BY VOICE
Abstract
An immunological method is proposed for solving the problem of text-independent identifi-cation of a person by voice, based on the principles of presentation and processing of voice infor-mation accepted in artificial immune systems. For personality identification by its voice, a Fanta model is used in which the voice signal is formed by passing through a high-order filter. Cepstral coefficients obtained on the basis of a linear speech predictor are used as feature vectors. The following analysis of the feature vectors is carried out on the basis of the apparatus of artificial immune systems using an immunological model of negative selection. The model implements de-centralized recognition of sequentially reaching speech fragments by comparing them with spe-cial, previously created recognition elements — V-detectors, represented by r-dimensional hyperspheres of variable size. V-detectors fill all the workspace free from points of the voice standard, imitating immunocompetent cells of the immune system. The comparison of fragments of the voice signal with V-detectors is carried out by checking their falling into the hyperspheres of V-detectors according to the principle of negative selection. The use of V-detectors makes it possi-ble to more effectively cover the working space of voice fragments by a significantly smaller num-ber of recognition elements, which reduces the computational cost of implementing the voice veri-fication procedure. During the speech signal analysis, the decision "well-known/stranger" is making based on a statistics of V-detectors response frequency. The method is intended for continuous verification control of the speaker’s identity at the rate of voice data income when text of arbitrary size and content is reproduced. It allows to make a timely decision about the possible substitution of speakers. The advantage of the method is its complete protection from replay attacks.
References
2. Zhang Sh.-X, Mak M.-W. A new adaptation approach to high-level speaker-model creation in speaker verification, Speech Communication, 2009, Vol. 51, pp. 534-550.
3. Pervushin E.A. Obzor osnovnykh metodov raspoznavaniya diktorov [Overview of basic speaker recognition methods], Matematicheskie struktury i modelirovanie [Mathematical structures and modeling], 2011, Issue 24, pp. 41-54.
4. Grishin V.M., Kalashnikov D.M. Rechevoy fragmentator dlya neyrosetevogo biometricheskogo vokodera [Speech fragmenter for neural network biometric vocoder], Penza-2012: Tr. nauchno-tekhnicheskoy konferentsii klastera penzenskikh predpriyatiy, obespechivayushchikh bezopasnost' informatsionnykh tekhnologiy [Penza-2012: Proceedings of the scientific and technical conference of the cluster of Penza enterprises providing security of information technologies]. Available at: http://pniei.rf/activity/science/BIT/T8-p73.pdf.
5. Lei Y., Hansen J. H.L. Mismatch modeling and compensation for robust speaker verification, Speech Communication, 2011, Vol. 53, pp. 257-268.
6. Makarevich O.B., Yurkov P.Yu., Fedorov V.M. Primenenie rekurrentnykh neyronnykh setey dlya tekstonezavisimoy identifikatsii diktora [The use of recurrent neural networks for text-independent speaker identification], Sb. trudov «Informatsionnaya bezopasnost'» [Collection of works "Information security"]. Taganrog, 2002, pp. 200-201.
7. Makarevich O.B., Babenko L.K., Fedorov V.M., Yurkov P.Yu. Tekstonezavisimaya autentifikatsiya/identifikatsiya po golosu v sistemakh upravleniya dostupom [Non-volatile au-thentication/voice identification in access control systems], X Vserossiyskaya nauchno-prakticheskaya konferentsiya «Problemy informatsionnoy bezopasnosti v sisteme vysshey shkoly» [X all-Russian scientific and practical conference "problems of information security in the system of higher education"]. Moscow: MIFI, 2003, pp. 28-29.
8. Bimbot F. et al. A Tutorial on Text-Independent Speaker Verification, EURASIP Journal on Applied Signal Processing, 2004, No. 4, pp. 430-451.
9. Fant G. Akusticheskaya teoriya recheobrazovaniya [Acoustic theory of speech formation]. M.: Nauka, 1964, 283 p.
10. Dasgupta D. Artificial Immune Systems and Their Applications, Ed., Springer-Verlag, 1999.
11. De Castro L.N., Timmis, J.I. Artificial Immune Systems: A New Computational Intelligence Approach. London: Springer-Verlag, 2000, 357 p.
12. Iskusstvennye immunnye sistemy i ikh primenenie [Artificial immune systems and their applica-tion], ed. by D. Dasgupty: transl. from engl. A.A. Romanyukhi. Moscow: Fizmatlit, 2006, 344 p.
13. Dasgupta D., Forrest S. Tool breakage detection in milling operations using a negative-selection algorithm, Technical report CS95-5, Department of computer science, University of New Mexico, 1995.
14. Forrest S., Perelson A.S., Allen L., Cherukuri R. Self-nonself discrimination in a computer, In: Proc. of Ieee symposium on research in security, Oakland, CA, 16-18 May 1994, pp. 202-212.
15. Opengeym A.V., Shafer R.V. Tsifrovaya obrabotka signalov [Digital signal processing]: transl. from engl., ed. by S.Ya. Shatsa. Moscow: Svyaz', 1979, 416 p.
16. Rabiner L.R., Shafer R.V. Tsifrovaya obrabotka rechevykh signalov [Digital processing of speech signals]: transl. from engl., ed. by M.V. Nazarova, Yu.N. Prokhorova. Moscow: Radio i svyaz', 1981, 495 p.
17. Markel Dzh., Grey A.Kh. Lineynoe predskazanie rechi [Linear prediction of speech]: transl. from engl., ed. by Yu.N. Prokhorova, V.S. Zvezdina. Moscow: Svyaz', 1980, 308 p.
18. Bryukhomitskiy Yu.A. Immunologicheskiy podkhod k organizatsii klaviaturnogo monitoringa [Immunological approach to the organization of keyboard monitoring], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2014, No. 2 (151), pp. 33-41.
19. Bryukhomitskiy Yu.A., Fedorov V.M. Metod tekstonezavisimoy identifikatsii lichnosti po golosu [Method of text-independent identification of personality by voice], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2018, No. 8 (202), pp. 173-181.
20. Ji Z., Dasgupta D. Real-valued negative selection algorithm with variable-sized detectors, Genetic and Evolutionary Computation (GECCO 2004): Proceedings. – Berlin–Heidelberg: Springer-Verlag, 2004. Ser. LNCS 3102, Part I, pp. 287-298.
21. Ji Z., Dasgupta D.V-Detector: An Efficient Negative Selection Algorithm with «Proba-bly Adequate» Detector Coverage, Information Sciences, 2009, Vol. 179, pp. 1390-1406.
22. Pourhabibi T., Azmi R. Anomaly Based IDS Using Variable Size Detector Generation in AIS: A Hybrid Approach, International Journal of Machine Learning and Computing, June 2012, Vol. 2, No. 3.
