SNAP:用于语音深度伪造检测中消除伪影投影的说话人消除
SNAP: Speaker Nulling for Artifact Projection in Speech Deepfake Detection
AI总结:
针对语音深度伪造检测中说话人信息干扰问题,提出SNAP框架通过消除说话人依赖成分,提升检测器对伪影特征的识别能力。
摘要:
近期文本到语音技术的进步使得生成高保真的合成语音几乎无法与真实语音区分。尽管最近的研究表明基于自监督学习的语音编码器在深度伪造检测中有效,但这些模型在未见过的说话人上泛化能力较差。我们的定量分析表明这些编码器表示受到说话人信息的显著影响,导致检测器利用说话人特定的相关性而非伪影相关线索。我们称这种现象为说话人纠缠。为减轻这种依赖,我们引入了SNAP,一种说话人消除框架。我们估计一个说话人子空间,并应用正交投影以抑制说话人依赖的成分,隔离残差特征中的合成伪影。通过减少说话人纠缠,SNAP促使检测器关注伪影相关模式,从而实现最先进的性能。
英文摘要:
Recent advancements in text-to-speech technologies enable generating high-fidelity synthetic speech nearly indistinguishable from real human voices. While recent studies show the efficacy of self-supervised learning-based speech encoders for deepfake detection, these models struggle to generalize across unseen speakers. Our quantitative analysis suggests these encoder representations are substantially influenced by speaker information, causing detectors to exploit speaker-specific correlations rather than artifact-related cues. We call this phenomenon speaker entanglement. To mitigate this reliance, we introduce SNAP, a speaker-nulling framework. We estimate a speaker subspace and apply orthogonal projection to suppress speaker-dependent components, isolating synthesis artifacts within the residual features. By reducing speaker entanglement, SNAP encourages detectors to focus on artifact-related patterns, leading to state-of-the-art performance.
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。