Interpretable Temporal Class Activation Representation for Audio Spoofing Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Menglu, Zhang, Xiao-Ping
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918103709908992
author Li, Menglu
Zhang, Xiao-Ping
author_facet Li, Menglu
Zhang, Xiao-Ping
contents 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 contributing to detection. Furthermore, we demonstrate that multi-label training based on spoofing types, rather than binary labels as bonafide and spoofed, enables the model to learn distinct characteristics of different attacks, significantly improving detection performance. Our model achieves state-of-the-art results, with an EER of 0.51% and a min t-DCF of 0.0165 on the ASVspoof2019-LA set.
format Preprint
id arxiv_https___arxiv_org_abs_2406_08825
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Interpretable Temporal Class Activation Representation for Audio Spoofing Detection
Li, Menglu
Zhang, Xiao-Ping
Sound
Cryptography and Security
Audio and Speech Processing
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 contributing to detection. Furthermore, we demonstrate that multi-label training based on spoofing types, rather than binary labels as bonafide and spoofed, enables the model to learn distinct characteristics of different attacks, significantly improving detection performance. Our model achieves state-of-the-art results, with an EER of 0.51% and a min t-DCF of 0.0165 on the ASVspoof2019-LA set.
title Interpretable Temporal Class Activation Representation for Audio Spoofing Detection
topic Sound
Cryptography and Security
Audio and Speech Processing
url https://arxiv.org/abs/2406.08825