分析自监督模型各层对语音深度伪造检测的贡献，发现低层特征最有效。
Comprehensive Layer-wise Analysis of SSL Models for Audio Deepfake Detection
- 逐层分析变压器模型在语音伪造检测中的表现
- 底层层特征判别力强，高层信息相关性弱，少量底层层即可达高精度
- 适合关注模型可解释性与推理效率的研究者
本文针对自监督学习（SSL）模型在语音深度伪造检测中的表现，开展跨多语言场景（英语、中文、西班牙语）、部分语音、歌曲及场景级伪造的系统性分层分析。通过评估不同变压器层的贡献，揭示了模型行为的关键洞见：底层始终提供最具判别性的特征，而高层捕捉的信息相关性较弱。值得注意的是，即使仅使用少数几层，所有模型仍能取得具有竞争力的等错误率（EER）表现。这表明，仅采用少量底层层即可显著降低计算开销并提升检测速度。本研究深化了对SSL模型在深度伪造检测中作用机制的理解，为多种语言和上下文场景下的应用提供了实用参考。所训练模型与代码已公开：https://github.com/Yaselley/SSL_Layerwise_Deepfake。
原文摘要 · Abstract (English)
This paper conducts a comprehensive layer-wise analysis of self-supervised learning (SSL) models for audio deepfake detection across diverse contexts, including multilingual datasets (English, Chinese, Spanish), partial, song, and scene-based deepfake scenarios. By systematically evaluating the contributions of different transformer layers, we uncover critical insights into model behavior and performance. Our findings reveal that lower layers consistently provide the most discriminative features, while higher layers capture less relevant information. Notably, all models achieve competitive equal error rate (EER) scores even when employing a reduced number of layers. This indicates that we can reduce computational costs and increase the inference speed of detecting deepfakes by utilizing only a few lower layers. This work enhances our understanding of SSL models in deepfake detection, offering valuable insights applicable across varied linguistic and contextual settings. Our trained models and code are publicly available: https://github.com/Yaselley/SSL_Layerwise_Deepfake.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。