What Does an Audio Deepfake Detector Focus on? A Study in the Time Domain

Abstract

Adding explanations to audio deepfake detection (ADD) models will enable insights on the decision making process and thus boost their real-world application. In this paper, we propose a relevancy-based explainable AI (XAI) method to analyze the predictions of transformer-based ADD models. We compare against standard Grad-CAM and SHAP-based methods, using quantitative faithfulness metrics as well as a partial spoof test, to comprehensively analyze the relative importance of different temporal regions in an audio. We consider large datasets, unlike previous works where only limited utterances are studied, and find that the XAI methods differ in their explanations. The proposed relevancy-based XAI method performs the best overall on a variety of metrics. Further investigation on the relative importance of speech/non-speech, phonetic content, and voice onsets/offsets suggests that the XAI results obtained from a limited set of utterances do not necessarily hold when evaluated on large datasets.