Browse > Article
http://dx.doi.org/10.3837/tiis.2020.01.010

A Robust Method for Speech Replay Attack Detection  

Lin, Lang (Faculty of Electrical Engineering and Computer Science, Ningbo University)
Wang, Rangding (Faculty of Electrical Engineering and Computer Science, Ningbo University)
Yan, Diqun (Faculty of Electrical Engineering and Computer Science, Ningbo University)
Dong, Li (Faculty of Electrical Engineering and Computer Science, Ningbo University)
Publication Information
KSII Transactions on Internet and Information Systems (TIIS) / v.14, no.1, 2020 , pp. 168-182 More about this Journal
Abstract
Spoofing attacks, especially replay attacks, pose great security challenges to automatic speaker verification (ASV) systems. Current works on replay attacks detection primarily focused on either developing new features or improving classifier performance, ignoring the effects of feature variability, e.g., the channel variability. In this paper, we first establish a mathematical model for replay speech and introduce a method for eliminating the negative interference of the channel. Then a novel feature is proposed to detect the replay attacks. To further boost the detection performance, four post-processing methods using normalization techniques are investigated. We evaluate our proposed method on the ASVspoof 2017 dataset. The experimental results show that our approach outperforms the competing methods in terms of detection accuracy. More interestingly, we find that the proposed normalization strategy could also improve the performance of the existing algorithms.
Keywords
Automatic speaker verification; replay attacks; channel effect; robustness; post-processing;
Citations & Related Records
연도 인용수 순위
  • Reference
1 D. Zhu, B. Ma and H. Li, "Speaker verification with feature-space MAPLR parameters," IEEE Transactions on Audio Speech &Language Processing, vol. 19, no. 3, pp. 505-515, April, 2011.   DOI
2 Z. Wu, T. Kinnunen, S. Chng and H.Li, "A study on spoofing attack in state-of-the-art speaker verification: the telephone speech case," in Proc. of Signal & Information Processing Association Annual Summit and Conference, pp. 1-5, December 03-06, 2012.
3 W. Shang and M. Stevenson, "A Playback Attack Detector for Speaker Verification Systems," in Proc. of International Symposium on Communications Control and Signal Processing, pp.1144-1149, March 12-14, 2008.
4 G. Jakub, G. Marcin and S. Rafal, "Playback attack detection for text-dependent speaker verification over telephone channels," Speech Communication, vol.67, pp.143-153, March, 2015.   DOI
5 Z. Wang, G. Wei and H. He, "Channel pattern noise based playback attack detection algorithm for speaker recognition," in Proc. of International Conference on Machine Learning and Cybernetics, pp.1708-1713, July10-13, 2011.
6 H. Delgado, M. Todisco andM. Sahidullah, "ASVspoof 2017 Version 2.0: meta-data analysis and baseline enhancements," in Proc. of Odyssey 2018 - The Speaker and Language Recognition Workshop, pp.296-303, June 26-29, 2018.
7 P. Nagarsheth, E. Khoury, and K. Patil, "Replay attack detection using DNN for channel discrimination," in Proc. of INTERSPEECH 2017, pp. 97-101, August 22-24, 2017.
8 M. Todisco, H. Delgado and N. Evans, "A New Feature for Automatic Speaker Verification Anti-Spoofing: Constant Q Cepstral Coefficients," in Proc. of Odyssey 2016 - The Speaker and Language Recognition Workshop, pp.283-290, June 21-24, 2016.
9 L. Li, Y. Chen and D. Wang, "A Study on Replay Attack and Anti-Spoofing for Automatic Speaker Verification," in Proc. of INTERSPEECH 2017, pp. 92-96, August 22-24, 2017.
10 K. Alluri, S. Achanta and S. Kadiri, "SFF Anti-Spoofer: IIIT-H Submission for Automatic Speaker Verification Spoofing and Countermeasures Challenge 2017," in Proc. of INTERSPEECH 2017, pp. 107-111, August 22-24, 2017.
11 R. Font1, J. Espm, M. Cano, R. Font, "Experimental analysis of features for replay attack detection-Results on the ASVspoof 2017 Challenge," in Proc. of INTERSPEECH 2017, pp. 7-11, August 22-24, 2017.
12 L. Lin, R Wang, D. Yan and C, Li, "A Replay Voice Detection Algorithm Based on Multi-feature Fusion," in Proc. of International Conference on Cloud Computing and Security, pp. 289-299, June 8-10, 2018.
13 L. Lin, R. Wang and D. Yan, "A Replay Speech Detection Algorithm Based on Sub-band Analysis," in Proc. of Intelligent Information Processing, pp. 337-345, October 19-22, 2018.
14 M. Saranya, R. Padmanabhan and H. Murthy, "Replay Attack Detection in Speaker Verification Using non-voiced segments and Decision Level Feature Switching," in Proc. of SPCOM 2018, pp. 332-336, June 2018.
15 B. Rafi, R. Murty and S. Naya, "A new approach for robust replay spoof detection in ASV systems," in Proc. of 2017 IEEE Global Conference on Signal and Information Processing, pp. 1-5, November 14-16, 2018.
16 H. Boril and L. Hansen, "UT-Scope: Towards LVCSR under Lombard effect induced by varying types and levels of noisy background," in Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing, pp.4472- 4475, May 22-27, 2011.
17 B. Atal, "Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification," Journal of the Acoustical Society of America, vol. 55, no. 6, pp. 1304-1312, June 1974.   DOI
18 O. Viikki and K. Laurila, "Noise robust HMM-based speech recognition using segmental cepstral feature vector normalization," in Proc. of Esca Nato Workshop on Robust Speech Recognition for Unknown Communication Channels, pp. 107-110. January 1997.
19 S. Yoshizawa, N. Hayasaka, N.Wada and Y. Miyanaga, "Cepstral gain normalization for noise robust speech recognition," in Proc. of IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 209-212, May,17-21,2004.
20 H. Boril and L. Hansen, "Unsupervised equalization of Lombard effect for speech recognition in noisy adverse environment," in Proc. of the IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 3937-3940, April 19-24, 2009.
21 T. Kinnunen, M. Sahidullah, M. Falcone, "RedDots replayed: A new replay spoofing attack corpus for text-dependent speaker verification research," in Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 5395-5399, March 5-9, 2017.
22 K. Lee, A. Larcher and G. Wang, "The reddots data collection for speaker recognition," in Proc. of INTERSPEECH 2015, pp. 2996-3000, September 6-10, 2015