Despite several years of research in deepfake and spoofing detection for automatic speaker verification, little is known about the artefacts that classifiers use to distinguish between bona fide and spoofed utterances. An understanding of these is crucial to the design of trustworthy, explainable solutions. In this paper we report an extension of our previous work to better understand classifier behaviour to the use of SHapley Additive exPlanations (SHAP) to attack analysis. Our goal is to identify the artefacts that characterise utterances generated by different attacks algorithms. Using a pair of classifiers which operate either upon raw waveforms or magnitude spectrograms, we show that visualisations of SHAP results can be used to identify attack-specific artefacts and the differences and consistencies between synthetic speech and converted voice spoofing attacks.
翻译:尽管经过多年的深层假言和假言检测研究,以进行自动扬声器核查,但对于分类者用来区分善意和伪言的手工艺品却知之甚少,了解这些手工艺品对于设计可信赖、可解释的解决办法至关重要。在本文中,我们报告了我们以前为更好地理解分类行为而开展的工作的延伸,以更好地了解沙普利·Additive Explectations (SHAP) 来攻击分析。我们的目标是查明不同攻击算法所产生言论特征的手工艺品。我们使用一组以原始波形或规模光谱操作的分类师,我们展示了SHAP结果的可视化可用于识别特定攻击性的手工艺品,以及合成言词和转换语音波音攻击之间的差别和构成。