Spoofing and countermeasures for speaker verification

作者: Zhizheng Wu , Nicholas Evans , Tomi Kinnunen , Junichi Yamagishi , Federico Alegre

DOI: 10.1016/J.SPECOM.2014.10.005

关键词:

摘要: While biometric authentication has advanced significantly in recent years, evidence shows the technology can be susceptible to malicious spoofing attacks. The research community responded with dedicated countermeasures which aim detect and deflect such Even if literature that they effective, problem is far from being solved; systems remain vulnerable spoofing. Despite a growing momentum develop for automatic speaker verification, now matured sufficiently support mass deployment an array of diverse applications, greater effort will needed future ensure adequate protection against This article provides survey past work identifies priority directions future. We summarise previous studies involving impersonation, replay, speech synthesis voice conversion attacks more efforts countermeasures. should address lack standard datasets over-fitting existing specific, known

参考文章(158)
John Thompson, James Hopgood, Saurav Sthapit, Neil Robertson, European Signal Processing Conference (EUSIPCO) ,(2016)
Chen-Yu Yang, Ling-Hui Chen, Zhen-Hua Ling, Li-Rong Dai, Xian-Jun Xia, Yang Song, The USTC System for Blizzard Challenge 2012 ,(2012)
A·瑞丘德芮, A·P·兰加拉杰, M·E·戴舍尔, M·赞纳图, W·M·贝尔特曼, Speech audio process ,(2011)
Tomi Kinnunen, Haizhou Li, Kong Aik Lee, Zhizheng Wu, Filip Sedlak, E. S. Chng, Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on international conference on acoustics, speech, and signal processing. ,(2012) , 10.1109/ICASSP.2012.6288895
Oliver Watts, Simon King, Heng Lu, Combining a Vector Space Representation of Linguistic Context with a Deep Neural Network for Text-To-Speech Synthesis 8th ISCA Speech Synthesis Workshop. pp. 261- 265 ,(2013)
Mark Ordowski, Mark A. Przybocki, Alvin F. Martin, George R. Doddington, Terri Kamm, The DET Curve in Assessment of Detection Task Performance conference of the international speech communication association. ,(1997)
D. Sundermann, H. Ney, VTLN-based voice conversion international symposium on signal processing and information technology. pp. 556- 559 ,(2003) , 10.1109/ISSPIT.2003.1341181
Takashi Masuko, Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura, Takayoshi Yoshimura, Simultaneous Modeling of Spectrum, Pitch and Duration in HMM-Based Speech Synthesis conference of the international speech communication association. pp. 2347- 2350 ,(1999)
Mats Blomberg, Johan Lindberg, Vulnerability in speaker verification. A study of technical impostor techniques conference of the international speech communication association. pp. 1211- 1214 ,(1999)
Junichi Yamagishi, P.L. De Leon, M. Pucher, Evaluation of the Vulnerability of Speaker Verification to Synthetic Speech Odyssey. pp. 28- ,(2010)