arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.03237cs.SDeess.AS
收藏

基于深度稳定学习的广义伪造音频检测

Generalized Fake Audio Detection via Deep Stable Learning

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, Chinese Academy of Sciences(中国科学院人工智能学院);Tsinghua University(清华大学);Communication University of China(中国传媒大学);Shanghai Polytechnic University(上海第二工业大学)

Zhiyong Wang, Ruibo Fu, Zhengqi Wen, Yuankun Xie, Yukun Liu, Xiaopeng Wang, Xuefei Liu, Yongwei Li, Jianhua Tao, Yi Lu, Xin Qi, Shuchen Shi

AI总结:

本文提出一种基于稳定学习的样本权重学习(SWL)模块,通过特征去相关解决伪造音频检测中的分布偏移问题,无需额外数据即可提升多种模型在不同分布数据集上的泛化能力。

摘要:

尽管当前的伪造音频检测方法在特定数据集上取得了显著成功,但在使用不同分布的数据集进行评估时往往表现不佳。以往研究通常通过关注使用额外数据或在训练过程中施加额外损失约束来处理分布偏移。然而,这些方法要么需要大量数据,要么会使训练过程复杂化。在本工作中,我们提出了一种基于稳定学习的训练方案,该方案包含一个样本权重学习(SWL)模块,通过从训练样本中学习权重来对所有选定特征进行去相关,从而解决分布偏移问题。所提出的便携式即插即用型SWL易于应用于多个基础模型,并在训练过程中无需使用额外数据即可使其具备泛化能力。在ASVspoof数据集上进行的实验清楚地证明了SWL在来自不同分布的三个评估数据集上对不同模型进行泛化的有效性。

英文摘要:

Although current fake audio detection approaches have achieved remarkable success on specific datasets, they often fail when evaluated with datasets from different distributions. Previous studies typically address distribution shift by focusing on using extra data or applying extra loss restrictions during training. However, these methods either require a substantial amount of data or complicate the training process. In this work, we propose a stable learning-based training scheme that involves a Sample Weight Learning (SWL) module, addressing distribution shift by decorrelating all selected features via learning weights from training samples. The proposed portable plug-in-like SWL is easy to apply to multiple base models and generalizes them without using extra data during training. Experiments conducted on the ASVspoof datasets clearly demonstrate the effectiveness of SWL in generalizing different models across three evaluation datasets from different distributions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑