Interpretable Temporal Class Activation Representation for Audio Spoofing Detection

arXiv:2406.08825v1 Announce Type: cross
Abstract: Explaining the decisions made by audio spoofing detection models is crucial for fostering trust in detection outcomes. However, current research on the interpretability of detection models is limited to applying XAI tools to post-trained models. In this paper, we utilize the wav2vec 2.0 model and attentive utterance-level features to integrate interpretability directly into the model's architecture, thereby enhancing transparency of the decision-making process. Specifically, we propose a class activation representation to localize the discriminative frames …

arxiv audio class cs.cr cs.sd current detection eess.as outcomes representation research spoofing temporal tools trust xai