APPLICATION OF THE VOICE IDENTIFICATION METHOD ADAPTED TO THE QUIET PRESENCE OF PASSWORD PHRASES TO COUNTER THE LEAKAGE OF SPEECH INFORMATION
The article discusses the features of biometric voice identification under the condition of quiet pronunciation of password phrases. Biometric voice identification differs significantly from standard identification systems and access control systems using symbolic passwords and keys. Biometric voice identification is based on unique and individual characteristics of identity and virtually eliminates the possibility of unauthorized actions associated with loss, theft or transfer of the password to third parties. The widespread use of biometric voice identification systems entails increased interest on the part of malefactors. The most frequent are attacks using previously used biometric features, for example, audio recording of a passphrase. To minimize the attacks described above, a biometric voice identification method, based on the whitening filter method, adapted to the quiet pronunciation of passphrases has been proposed. Described is the software implementation of the proposed method - "Information system for identifying speakers by voice", which allows biometric identification by voice, provided that password phrases are quietly uttered to counteract the leakage of speech information through acoustic channels.
Vasiliev R.A. Application of the voice identification method adapted to the quiet presence of password phrases to counter the leakage of speech information // Research result. Information technologies. – Т.6, №1, 2021. – P. 20-29. DOI: 10.18413/2518-1092-2021-6-1-0-3
While nobody left any comments to this publication.
You can be first.
1. Nikolaev D.B, Vasiliev R.A. Analysis of the possibility of using voice identification in systems for differentiating access to information // Research result. Information technologies. – 2016. – T. 1. – Issue 1. – P. 48-57.
2. Savchenko V.V., Vasiliev R.A. Analysis of the emotional state of the speakers by voice based on the phonetic lie detector // Scientific Bulletin of Belgorod State University. – 2014. – Issue. – No. 21 (192). – P. 186-195.
3. Vasiliev R.A. Svid. about the state. registration of the computer program No. 2015663306. Program for the identification of speakers by voice // Vasiliev R.А. Registered. 15.12.2015 – M.: Rospatent, 2015.
4. Buzov GA Protection from information leakage through technical channels. – M., 2005.
5. Tsypkin Ya.Z. Adaptation and training in automatic systems. Moscow: Nauka, 1968.
6. Savchenko V.V. Information theory of speech perception. // Izv. universities of Russia. Radio electronics. 2007. – Issue. 6, pp. 3–9.
7. Savchenko V.V. Information-theoretic substantiation of the Gaussian signal model in problems of automatic speech recognition. // Izv. universities of Russia. Radio electronics. 2008. –Issue. 1. – P. 24–33.
8. Savchenko V.V., Akat'ev D.Yu., Karpov N.V. Automatic recognition of elementary speech units by the whitening filter method // Izv. universities of Russia. Radio electronics. 2007. Issue 4. P. 11-19.
9. Potapova RK Speech: communication, information, cybernetics: Textbook, manual. 2nd ed. – M.: Editorial URSS, 2001.
10. Kullback S. Information theory and statistics. Moscow: Nauka, 1967.
11. Vasiliev R.A. Biometric identification of users of information systems based on a cluster model of elementary speech units: Dis. ... to those of those. sciences. M., 2017.153 p.
12. Vasiliev R.A. Investigation of the phonetic structure of speech and identification of speakers by voice // Security of information technologies. 2013. – T. 20. –No. 1. – P. 85-86.
13. Vasiliev R.A. Investigation of the peculiarities of the phonetic structure of speech and text-independent identification of speakers by continuous speech // Information security of regions. – 2012. – No. 2(11). – P. 57-63.
14. Vasiliev R.A. Application of methods of phonetic analysis of speech for identifying emotionally stable and unstable university students // Scientific result // Series: Information technologies. Belgorod State University. 2020. –Vol. 5. – No. 2. – P. 9-17.
15. Volobuev SV Otsenka acoustical security with the use of tools. // Security systems for communications and telecommunications. – 1999. – № 25. – P. 38-45.
16. Agranovsky A.B., Lednov D.A. Method of text-independent user identification based on the individuality of pronunciation of vowel sounds // Acoustics and Applied Linguistics: Yearbook of the Russian Academy of Education. – M.: 2002. – Issue 3. – P. 103-115.
17. Garofolo J., Auzanne G., and Voorhees E. The trec spoken document retrieval track: A success story. // In proceedings of the Recherche d'Informations Assiste par Ordinateur: Content Based Multimedia Information Access Conference, 2000. – pp. 1-20.
18. Gray A., Markel J. Distance measures for speech processing // IEEE Trans. On Acoust., Speech and Lang. processing. oct. 1976. – Vol. 24(5) – p. 291-380.
19. Mamou J., Mass Y., Ramabhadran B., Sznajder B. Combination of multiple speech transcription methods for vocabulary independent search // In proceedings of the ACM SIGIR Workshop `Searching Spontaneous Conversational Speech. Singapore. – 2008. – pp. 20-27.
20. Huijbregts M., Ordelman R., Jong F. Annotation of heterogeneous multimedia content using automatic speech recognition // In Proceedings of the second international conference on Semantics And digital Media Technologies (SAMT). Lecture Notes in Computer Science. Berlin Springer Verlag. December 2007. – pp. 78-90.