On the study of replay and voice conversion attacks to text-dependent speaker verification
On the study of replay and voice conversion attacks to text-dependent speaker verification
复制标题
DOI：
10.1007/s11042-015-3080-9
复制
发表时间：
2016-05
影响因子：
3.6
通讯作者：
Zhizheng Wu;Haizhou Li
中科院分区：
文献类型：
--
作者：
Zhizheng Wu;Haizhou Li
自动说话人验证(ASV)是基于语音样本自动接受或拒绝所声称的身份。最近，个别研究证实了最新的与文本无关的ASV系统在重放、语音合成和语音转换攻击下的脆弱性。然而，面对各种欺骗攻击，依赖于文本的ASV系统的行为还没有得到系统的评估。在这项工作中，我们首先对文本相关的ASV系统进行了系统的分析，利用相同的协议和数据库，特别是代表移动设备质量语音的RSR2015数据库，进行了重放和语音转换攻击。然后，通过将语音转换客观评价指标与说话人验证错误率联系起来，分析语音转换与说话人确认之间的相互作用，从语音转换的角度分析语音转换的脆弱性。
Automatic speaker verification (ASV) is to automatically accept or reject a claimed identity based on a speech sample. Recently, individual studies have confirmed the vulnerability of state-of-the-art text-independent ASV systems under replay, speech synthesis and voice conversion attacks on various databases. However, the behaviours of text-dependent ASV systems have not been systematically assessed in the face of various spoofing attacks. In this work, we first conduct a systematic analysis of text-dependent ASV systems to replay and voice conversion attacks using the same protocol and database, in particular the RSR2015 database which represents mobile device quality speech. We then analyse the interplay of voice conversion and speaker verification by linking the voice conversion objective evaluation measures with the speaker verification error rates to take a look at the vulnerabilities from the perspective of voice conversion.