DuRe-ST：用于语音深度伪造检测的双关系频谱-时间建模
DuRe-ST: Dual-Relation Spectro-Temporal Modeling for Speech Deepfake Detection
- The Hong Kong Polytechnic University（香港理工大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
针对语音深度伪造检测忽略频谱-时间协变的问题，提出DuRe-ST模型，联合协方差与图注意力关系建模，在ASVspoof等基准上相对EER降低25.9%-28.4%，且参数增量小。
中文摘要 AI 辅助
以往的语音深度伪造检测器能够通过图注意力自适应地捕获频谱-时间依赖关系，但它们在很大程度上忽略了频谱表示与时间表示之间的协变关系。为解决这一不足，我们从它们的联合协方差构建归一化亲和力图，并应用多项式图滤波来捕获高阶协方差诱导的依赖关系。我们首先开发了Cov-ST，以单独评估基于协方差的关系建模的贡献。尽管它提升了检测性能，但其对多项式阶数的敏感性表明，单独建模协方差关系时鲁棒性有限。因此，我们提出了DuRe-ST，它联合利用协方差诱导关系和图注意力诱导关系，以捕获互补的二阶协变和自适应频谱-时间依赖。实验表明，在ASVspoof基准上，DuRe-ST相比XLSR-AASIST实现了平均相对等错误率（EER）降低25.9%，在四个跨数据集基准上平均降低28.4%，且仅增加了4-8k个可训练后端参数。此外，在四个基准上，其相对EER比现有最强的公开可比模型低2.2-13.2%，同时模型规模小于所考虑的公开模型。
英文摘要
Previous speech deepfake detectors can adaptively capture spectro-temporal dependencies through graph attention, yet they largely overlook the co-variation between spectral and temporal representations. To address this gap, we construct a normalized affinity graph from their joint covariance and apply polynomial graph filtering to capture higher-order covariance-induced dependencies. We first develop Cov-ST to isolate the contribution of covariance-based relational modeling. Although it improves detection performance, its sensitivity to the polynomial order suggests limited robustness when covariance relations are modeled alone. We therefore propose DuRe-ST, which jointly exploits covariance-induced and graph-attention-induced relations to capture complementary second-order co-variation and adaptive spectro-temporal dependencies. Experiments show that DuRe-ST achieves an average relative EER reduction of 25.9% over XLSR-AASIST on the ASVspoof benchmarks and 28.4% across four cross-dataset benchmarks with only 4-8k additional trainable back-end parameters. It further outperforms the strongest publicly available comparison models by 2.2-13.2% in relative EER on four benchmarks, while remaining smaller than the publicly available models considered.
