使用特定伪迹专家和校准检测分数进行可解释的语音深度伪造检测
Toward Interpretable Speech Deepfake Detection using Artifact-Specific Experts and Calibrated Detection Scores
- DEIB, Politecnico di Milano（米兰理工大学 电子、信息与生物工程系）
- National Institute of Informatics（国立情报学研究所）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对语音深度伪造检测提出基于特定伪迹专家模型的框架，各专家检测特定伪迹并输出校准分数，经集成进行真假分类，保持可解释性，能捕捉合成语音可解释信号。
AI中文摘要：
在这项工作中，我们提出了一个基于特定伪迹专家模型的可解释语音深度伪造检测框架。该框架不依赖黑盒决策，而是提供人类可理解的证据，这在高风险环境中至关重要。每个专家经过训练以检测特定语音合成伪迹，其输出被校准为对数似然比作为可解释的证据分数。我们评估了五个特定伪迹专家，表明经过适当校准，它们能捕捉目标伪迹并产生有意义的证据。重要的是，每个专家仅估计其分配伪迹的存在，其输出汇总成一个集成来进行实际的真假分类，同时保持可解释性，指出每个专家对伪造分类的支持或矛盾程度。结果表明特定伪迹专家能捕捉跨多代管道的合成语音的可解释信号。
英文摘要：
In this work, we propose an interpretable framework for speech deepfake detection based on artifact-specific expert models. Rather than relying on black-box decisions, the framework provides human-understandable evidence, which is critical in high-stakes settings. Each expert is trained to detect a specific speech synthesis artifact, and its output is calibrated into a log-likelihood ratio that serves as an interpretable evidence score. We evaluate five artifact-specific experts and show that, with proper calibration, they can capture their target artifacts and produce meaningful evidence. Importantly, each expert estimates only the presence of its assigned artifact rather than directly performing the final decision. Their outputs are aggregated into an ensemble to produce the actual real-versus-fake classification, while maintaining interpretability by indicating how strongly each expert supports or contradicts a fake classification. Results show that artifact-specific experts capture interpretable signals of synthetic speech across multiple generation pipelines.
