Replay attack detection based on distortion by loudspeaker for voice authentication
Replay attack detection based on distortion by loudspeaker for voice authentication
复制标题
基于扬声器失真的语音认证重放攻击检测
DOI：
10.1007/s11042-018-6834-3
复制
发表时间：
2018-11
影响因子：
3.6
通讯作者：
Changwen Chen
中科院分区：
文献类型：
--
作者：
Yanzhen Ren;Zhong Fang;Dengkai Liu;Changwen Chen
基于自动说话人验证（ASV）的身份认证受到了广泛关注。在许多应用中，语音可以代替密码。然而，当前ASV系统的安全性受到了许多恶意欺骗攻击的严重挑战。在所有这些攻击中，重播攻击是对ASV系统最大的威胁之一，攻击者可以使用合法用户的预先录制的语音样本访问ASV系统。在本文中，我们提出了一种重放攻击检测（RAD）方案来区分正常语音和重放语音。本文针对扬声器引起的失真：低频衰减和高频谐波，提出了一套RAD特征DL-RAD，包括谐波能量比（HER）、低谱比（LSR）、低谱方差（LSV）和低谱差方差（LSDV），以描述正常语音信号和重放语音信号之间的不同特征。采用支持向量机作为分类器来评价这些特征的性能。实验结果表明，该方法的真阳性率（TPR）和真负率（TNR）分别约为98.15%和98.75%，明显优于现有方案。该方案既适用于依赖文本的ASV系统，也适用于不依赖文本的ASV系统。
Identity authentication based on Automatic Speaker Verification (ASV) has attracted extensive attention. Voice can be used as a substitute of password in many applications. However, the security of current ASV systems has been seriously challenged by many malicious spoofing attacks. Among all those attacks, replay attack is one of the biggest threats to the ASV System, where an adversary can use a pre-recorded speech sample of the legal user to access the ASV system. In this paper, we present a replay attack detection (RAD) scheme to distinguish normal speech and replayed speech. We focus on the distortion caused by loudspeaker: low-frequency attenuation and high-frequency harmonics, and present a suite of RAD features DL-RAD, including Harmonic Energy Ratio (HER), Low Spectral Ratio (LSR), Low Spectral Variance (LSV), and Low Spectral Difference Variance (LSDV), to describe the different characteristics between the normal speech signal and replay speech signal. SVM is adopted as a classifier to evaluate the performance of these features. Experiment results show that the True Positive Rate (TPR), True Negative Rate (TNR) of the proposed method are about 98.15% and 98.75% respectively, which are significantly better than the existing scheme. The proposed scheme can be applied to both text-dependent and text-independent ASV systems.
登录
查看更多内容
用于区分摄影图像和计算机图形的四元数小波域取证特征分析
影响因子：
3.6
作者：
Wang, Jinwei;Li, Ting;Ye, Jingyu
通讯作者：
Ye, Jingyu
DOI：
--
发表时间：
2008
期刊：
Journal of Tsinghua University
影响因子：
--
作者：
Zheng Fang
通讯作者：
Zheng Fang
DOI：
10.21437/interspeech.2015-92
发表时间：
2015-09
期刊：
--
影响因子：
--
作者：
Sayaka Shiota;F. Villavicencio;J. Yamagishi;Nobutaka Ono;I. Echizen;T. Matsui
通讯作者：
Sayaka Shiota;F. Villavicencio;J. Yamagishi;Nobutaka Ono;I. Echizen;T. Matsui
DOI：
10.21437/eurospeech.1999-283
发表时间：
1999-09
期刊：
--
影响因子：
--
作者：
J. Lindberg;M. Blomberg
通讯作者：
J. Lindberg;M. Blomberg
影响因子：
3.6
作者：
Zhizheng Wu;Haizhou Li
通讯作者：
Zhizheng Wu;Haizhou Li