BreathNet: 通过呼吸提示引导的特征细化实现通用音频深度伪造检测
BreathNet: Generalizable Audio Deepfake Detection via Breath-Cue-Guided Feature Refinement
AI总结：
BreathNet通过整合呼吸信息提升音频深度伪造检测的泛化能力，采用BreathFiLM和多损失函数实现更有效的特征区分。
摘要：
随着深度伪造音频变得越来越真实和多样化，开发具有通用性的防御系统变得至关重要。现有的检测方法主要依赖XLS-R前端特征来提高泛化能力。然而，其性能仍然有限，部分原因是对细粒度信息的关注不足，例如生理提示或频域特征。在本文中，我们提出BreathNet，一种新颖的音频深度伪造检测框架，整合了细粒度的呼吸信息以提高泛化能力。具体来说，我们设计了BreathFiLM，一种特征级线性调制机制，该机制根据呼吸声的存在情况选择性地放大时间表示。BreathFiLM与XLS-R提取器联合训练，从而促使提取器学习并编码呼吸相关提示到时间特征中。然后，我们使用频率前端提取频谱特征，这些特征随后与时间特征融合，以提供由语音编码器或压缩伪影引入的互补信息。此外，我们提出了一组特征损失，包括正样本监督对比损失（PSCL）、中心损失和对比损失。这些损失共同增强判别能力，促使模型在特征空间中更有效地分离真实和深度伪造样本。在五个基准数据集上的广泛实验显示了最先进的性能。使用ASVspoof 2019 LA训练集，我们的方法在四个相关评估基准上实现了1.99%的平均EER，特别是在In-the-Wild数据集上，其EER为4.70%。此外，在ASVspoof5评估协议下，我们的方法在最新基准上实现了4.94%的EER。
英文摘要：
As deepfake audio becomes more realistic and diverse, developing generalizable countermeasure systems has become crucial. Existing detection methods primarily depend on XLS-R front-end features to improve generalization. Nonetheless, their performance remains limited, partly due to insufficient attention to fine-grained information, such as physiological cues or frequency-domain features. In this paper, we propose BreathNet, a novel audio deepfake detection framework that integrates fine-grained breath information to improve generalization. Specifically, we design BreathFiLM, a feature-wise linear modulation mechanism that selectively amplifies temporal representations based on the presence of breathing sounds. BreathFiLM is trained jointly with the XLS-R extractor, in turn encouraging the extractor to learn and encode breath-related cues into the temporal features. Then, we use the frequency front-end to extract spectral features, which are then fused with temporal features to provide complementary information introduced by vocoders or compression artifacts. Additionally, we propose a group of feature losses comprising Positive-only Supervised Contrastive Loss (PSCL), center loss, and contrast loss. These losses jointly enhance the discriminative ability, encouraging the model to separate bona fide and deepfake samples more effectively in the feature space. Extensive experiments on five benchmark datasets demonstrate state-of-the-art (SOTA) performance. Using the ASVspoof 2019 LA training set, our method attains 1.99% average EER across four related eval benchmarks, with particularly strong performance on the In-the-Wild dataset, where it achieves 4.70% EER. Moreover, under the ASVspoof5 evaluation protocol, our method achieves an EER of 4.94% on this latest benchmark.
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。
