Voice authentication based on the Russian-language dataset, MFCC method and the anomaly detection algorithm

• Autorzy: Sidorova Anna , Kogos Konstantin

Identyfikatory

DOI

10.15439/2020F43

• Konferencja: Federated Conference on Computer Science and Information Systems (15 ; 06-09.09.2020 ; Sofia, Bulgaria)
• Języki publikacji: EN

Abstrakty

EN

Almost all people's data is stored on their personal devices. For this reason, there is a need to protect information from unauthorized access by means of user authentication. PIN codes, passwords, tokens can be forgotten, lost, transferred, brute-force attacked. For this reason, biometric authentication is gaining in popularity. Biometric data are unchanged for a long time, different for users, and can be measured. This paper explores voice authentication due to the ease of use of this technology, since obtaining voice characteristics of users doesn't require an equipment in addition to the microphone, which is built into almost all devices. The method of voice authentication based on an anomaly detection algorithm has been proposed. The software module for text-independent authentication has been developed on the Python language. It's based on a new Mozilla's open source voice dataset "Common voice". Experimental results confirmed the high accuracy of authentication by the proposed method.

Słowa kluczowe

EN

authorisation; biometrics; cepstral analysis; natural language processing; speaker recognition

PL

autoryzacja; biometria; analiza cepstralna; przetwarzanie języka naturalnego; rozpoznawanie mówcy

• Wydawca: Polskie Towarzystwo Informatyczne
• Czasopismo: Annals of Computer Science and Information Systems
• Rocznik: 2020
• Tom: Vol. 21
• Strony: 537--540
• Opis fizyczny: Bibliogr. 14 poz., rys., tab.

Twórcy

autor

Sidorova Anna

• MEPHI Cryptology and cybersecurity department, Kashirskoe Sh. 31 Moscow, Russia

autor

Kogos Konstantin

• MEPHI Cryptology and cybersecurity department, Kashirskoe Sh. 31 Moscow, Russia

Bibliografia

• 1. Bernstein S.I., Kolokoltsev N.K., Ermolaeva V.V. Voice Authantication. Molodoy uchenyy[Young scientist], 2018, no.25. pp. 93-94. Available at: https://moluch.ru/archive/211/51686/ (accessed 24 April 2019)
• 2. Ermilov A.V. Metody, algoritmy i programmy resheniya zadach identifikatsii yazyka i diktora[Methods, algorithms and programs for solving problems of language and speaker identification]: Extended abstract of PhD dissertation (physics and mathematics), 2014, 22 p. (in Russian)
• 3. Ivanov D.A., Nikitin A.P. Text-dependent voice authentication method. Istoriya I arkhivy [History and archives], 2016, no. 3 (5). (in Russian)
• 4. Zakharova V.V. Razrabotka tekstonezavisimoy sistemy identifikatsii diktora na osnove fonemnogo razbieniya i GMM [Development of a text-independent speaker identification system based on phonemic partitioning and GMM]. Proceedings of the Science Conference of undergraduate and graduate students, Belorusskiy gosudarstvennyy universitet, Minsk, 2017, pp. 28-32. (in Russian)
• 5. Nogikh A.A., Solomatin D.I. Text-independent authentication. Sbornik studencheskikh nauchnykh rabot fakul'teta komp'yuternykh nauk VGU [Collection of student research papers of the faculty of computer science of VSU], 2016. pp. 117-123. (in Russian)
• 6. Jayamaha R. G. Voizlock-human voice authentication system using hidden markov model. Proceedings of the 4th International Conference on Information and Automation for Sustainability. IEEE, 2008. pp. 330-335.
• 7. Yan Z., Zhao S. A Usable Authentication System based on Personal Voice Challenge. Proceedings of the International Conference on Advanced Cloud and Big Data, 2016. pp. 194-199. DOI:10.1109
• 8. Shah, S. A. A., Shah S.W., A. ul Asar. Interactive Voice Response with Pattern Recognition Based on Artificial Neural Network Approach. NWFP University of Engineering and Technology, Peshawar, Pakistan, 2007. pp. 249-252.
• 9. J. Chang, D. Wang. Robust speaker recognition based on DNN/i-vectors and speech separation. Proceedings of the Acoustics, Speech and Signal Processing (ICASSP) IEEE International Conference, 2017. pp. 5415-5419.
• 10. Matveev Yu.N. Research of information content of speech signs for automatic speaker identification systems. Vestn. MGTU im. N. E. Baumana. Ser. Priborostroenie. Spetsial'nyy vypusk. Biometricheskie tekhnologii [Bulletin of the Bauman Moscow state technical University. Series “Instrument making”], 2013. no. 2. pp. 47-51. (in Russian)
• 11. Matveev Yu.N. Technologies for biometric identification of an individual by voice and other modalities. Vestn. MGTU im. N. E. Baumana. Ser. Priborostroenie. Spetsial'nyy vypusk. Biometricheskie tekhnologii [Bulletin of the Bauman Moscow state technical University. Series “Instrument making”. Special issue. “Biometric technology”.], 2012. No 3(3). pp. 46-61. (in Russian)
• 12. Sadykhov R.Kh., Rakush V.V. Models of Gaussian mixtures for speaker verification based on arbitrary speech. Doklady BGUIR [BSUIR reports], Minsk, 2003. no. 4 pp. 95-103. (in Russian)
• 13. Hundal J.K, Dr. Hamde S. T. Some Feature Extraction Techniques for Voice based Authentication System. Proceedings of the Power, Control, Signals and Instrumentation Engineering (ICPCSI) IEEE International Conference, 2017. pp. 419-421.
• 14. Documentation of python-speech-features. Available at: https://python-speech-features.readthedocs.io/en/latest/#welcome-to-python-speech-features-s-documentation (accessed: 20 March 2019).

Uwagi

1. Track 3: Network Systems and Applications

2. Technical Session: 1st International Forum on Cyber Security, Privacy and Trust

3. Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).