Automatically Trained TTS for Effective Attacks to Anti-spoofing System
This article is the proceeding of the priority research direction of the voice biometrics systems spoofing problem. We continue exploring speech synthesis spoofing attacks based on creating a text-to-speech voice. In our work we focused on the completely automatic way to create new voices for text-to-speech system and the investigation of the state-of-art spoofing detection system vulnerability to this spoofing attacks. Results obtained during our experiments demonstrate that 10 seconds of speech material is enough for EER increasement up to 19.67 %. Considering the fact, that automatic method for synthesis voiced training allows perpetrators to increase the amount of spoofing attacks to biometric systems, we raise the issue of relevance of a new type of spoofing attack, and development of the effective methods to detect it.
KeywordsSpoofing Anti-spoofing Speaker recognition TTS
This work was partially nancially supported by the Government of Russian Federation, Grant 074-U01.
- 2.Matveev, Y.N.: Biometric technologies of person identification by voice and other modalities. Vestnik MGTU. Priborostroenie 3(3), 46–61 (2012)Google Scholar
- 4.Novoselov, S., Pekhovsky, T., Simonchik, K.: STC speaker recognition system for the NIST i-vector challenge. In: Proceedings of the Odyssey 2014 - The Speaker and Language Recognition Workshop (2014)Google Scholar
- 5.Villalba, E., Lleida, E.: Speaker verification performance degradation against spoofing and tampering attacks. In: Proceedings of the FALA 2010 Workshop, pp. 131–134 (2010)Google Scholar
- 6.Shchemelinin, V., Topchina, M., Simonchik, K.: Vulnerability of voice verification systems to spoofing attacks by TTS voices based on automatically labeled telephone speech. In: Ronzhin, A., Potapova, R., Delic, V. (eds.) SPECOM 2014. LNCS, vol. 8773, pp. 475–481. Springer, Heidelberg (2014). (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics) Google Scholar
- 8.Wu, Z., et al.: ASVspoof 2015: the first automatic speaker verification spoofing and countermeasures challenge 2015. http://www.spoofingchallenge.org/is2015_asvspoof.pdf
- 9.Novoselov, S., et al.: STC Anti-spoofing systems for the ASVspoof 2015 challenge. http://ris.ifmo.ru/wp-content/uploads/2015/06/Technical_report_ASVspoof2015_STC.pdf
- 10.Dehak, N., et al. : Support vector machines versus fast scoring in the low-dimensional total variability space for speaker verification. In: Proceedings of the Interspeech, pp. 1559–1562 (2009)Google Scholar
- 11.Chistikov, P., Korolkov, E.: Data-driven speech parameter generation for russian text-to-speech system. computational linguistics and intellectual technologies. In: Proceedings of the Annual International Conference “Dialogue”, Issue 11(18), vol. 1. pp. 103–111 (2012)Google Scholar
- 12.Simonchik, K., Shchemelinn, V.: “STC SPOOFING” database for text-dependent speaker recognition evaluation. In: Proceedings of SLTU-2014 Workshop St. Petersburg, Russia, pp. 221–224 (2014)Google Scholar
- 14.Solomennik, A., Chistikov, P., Rybin, S., Talanov, A., Tomashenko, N.: Automation of new voice creation procedure for a russian TTS system. Vestnik MGTU. Priborostroenie 2, 29–32 (2013)Google Scholar
- 16.Wu, Z., et al.: A study on replay attack and anti-spoofing for text-dependent speaker verification. In: Proceedings of the Asia-Pacific Signal Information Processing Association Annual Summit and Conference (APSIPA ASC) (2014)Google Scholar