论文标题
来源跟踪：检测声音欺骗
Source Tracing: Detecting Voice Spoofing
论文作者
论文摘要
最近的反欺骗系统的重点是欺骗检测，该任务只是确定测试音频是否是假的。但是，很少有研究注意确定产生虚假语音的方法。逻辑访问（LA）场景中的常见欺骗攻击算法，例如语音转换和语音综合，可以分为几个阶段：输入处理，转换，波形生成等。在这项工作中，我们提出了一个用于对不同属性属性进行分类的系统，代表整个管道中不同模块的特征。除了确定整个欺骗管道以外，对欺骗攻击的属性进行分类可以使系统在不同阶段遇到不同模块的复杂组合时更加健壮。此外，我们的系统还可以用作反对看不见的欺骗方法的反欺骗的辅助系统。实验是在ASVSPOOF 2019 LA数据集上进行的，而所提出的方法对传统的二进制SPOOF检测方法实现了20 \％的相对改进。
Recent anti-spoofing systems focus on spoofing detection, where the task is only to determine whether the test audio is fake. However, there are few studies putting attention to identifying the methods of generating fake speech. Common spoofing attack algorithms in the logical access (LA) scenario, such as voice conversion and speech synthesis, can be divided into several stages: input processing, conversion, waveform generation, etc. In this work, we propose a system for classifying different spoofing attributes, representing characteristics of different modules in the whole pipeline. Classifying attributes for the spoofing attack other than determining the whole spoofing pipeline can make the system more robust when encountering complex combinations of different modules at different stages. In addition, our system can also be used as an auxiliary system for anti-spoofing against unseen spoofing methods. The experiments are conducted on ASVspoof 2019 LA data set and the proposed method achieved a 20\% relative improvement against conventional binary spoof detection methods.
