通过自合成伪假音频，让语音深伪检测器专注识别生成痕迹，提升泛化能力。
AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection
- 用真实音频自动生成伪假样本，强制说话人和语义一致
- 在7个数据集上平均错误率仅5.45%，波形伪造数据集降至1.23%
- 无需预先收集假音频，适合部署在无标注数据场景
生成模型的快速发展催生了高度逼真的语音深伪，但现有检测器存在严重偏差问题，导致在未见数据集上泛化性能差。本文提出针对生成痕迹的自合成方法（AFSS），通过自转换和自重构两种机制，从真实音频生成伪假样本。核心思想是施加同说话人约束，确保真实与伪假样本具有相同的说话人身份和语义内容，迫使检测器仅关注生成痕迹而非无关混淆因素。此外，引入可学习重加权损失，动态强化训练中合成样本的重要性。在7个数据集上的大量实验表明，AFSS达到当前最优性能，平均等错误率（EER）为5.45%，其中在WaveFake数据集上降至1.23%，In-the-Wild数据集上为2.70%，且完全摆脱对预收集假数据集的依赖。代码已公开于https://github.com/NguyenLeHaiSonGit/AFSS。
原文摘要 · Abstract (English)
The rapid advancement of generative models has enabled highly realistic audio deepfakes, yet current detectors suffer from a critical bias problem, leading to poor generalization across unseen datasets. This paper proposes Artifact-Focused Self-Synthesis (AFSS), a method designed to mitigate this bias by generating pseudo-fake samples from real audio via two mechanisms: self-conversion and self-reconstruction. The core insight of AFSS lies in enforcing same-speaker constraints, ensuring that real and pseudo-fake samples share identical speaker identity and semantic content. This forces the detector to focus exclusively on generation artifacts rather than irrelevant confounding factors. Furthermore, we introduce a learnable reweighting loss to dynamically emphasize synthetic samples during training. Extensive experiments across 7 datasets demonstrate that AFSS achieves state-of-the-art performance with an average EER of 5.45\%, including a significant reduction to 1.23\% on WaveFake and 2.70\% on In-the-Wild, all while eliminating the dependency on pre-collected fake datasets. Our code is publicly available at https://github.com/NguyenLeHaiSonGit/AFSS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。