HierCon：用于音频深度伪造检测的层次对比注意力
HierCon: Hierarchical Contrastive Attention for Audio Deepfake Detection
AI总结：
HierCon通过层次化层注意力框架和基于边界的对比学习，在音频深度伪造检测中实现更高效的领域不变嵌入建模，显著提升检测性能。
摘要：
现代TTS和语音转换系统生成的音频深度伪造越来越难以与真实语音区分开来，这引发了严重的安全和在线信任风险。尽管最先进的自监督模型提供了丰富的多层表示，但现有检测器将各层独立处理，忽略了对识别合成伪影至关重要的时间性和层次依赖性。我们提出了HierCon，一种结合基于边界的对比学习的层次化层注意力框架，该框架在时间帧、相邻层和层组之间建模依赖关系，同时鼓励领域不变的嵌入。在ASVspoof 2021 DF和In-the-Wild数据集上评估，我们的方法取得了最先进的性能（1.93%和6.87%的EER），相比独立层加权分别提高了36.6%和22.5%。结果和注意力可视化确认，层次建模增强了对跨领域生成技术和录音条件的泛化能力。
英文摘要：
Audio deepfakes generated by modern TTS and voice conversion systems are increasingly difficult to distinguish from real speech, raising serious risks for security and online trust. While state-of-the-art self-supervised models provide rich multi-layer representations, existing detectors treat layers independently and overlook temporal and hierarchical dependencies critical for identifying synthetic artefacts. We propose HierCon, a hierarchical layer attention framework combined with margin-based contrastive learning that models dependencies across temporal frames, neighbouring layers, and layer groups, while encouraging domain-invariant embeddings. Evaluated on ASVspoof 2021 DF and In-the-Wild datasets, our method achieves state-of-the-art performance (1.93% and 6.87% EER), improving over independent layer weighting by 36.6% and 22.5% respectively. The results and attention visualisations confirm that hierarchical modelling enhances generalisation to cross-domain generation techniques and recording conditions.
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。
