小模型也能抗干扰：多语言预训练让紧凑模型媲美大模型
Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTOR
- 用统一融合框架对比HuBERT与WavLM等紧凑模型
- 100M参数模型通过多语言预训练达到商用系统水平
- 发现模型鲁棒性来自预训练路径而非模型大小
自监督学习（SSL）是现代语音深度伪造检测的基础，但以往研究多集中于单一大型wav2vec2-XLSR骨干网络，对紧凑模型关注不足。本文提出RAPTOR——一种面向跨域识别的表征感知成对门控变压器，并在统一的成对门控融合检测器中，对HuBERT和WavLM系列紧凑模型进行了控制性研究，覆盖14个跨域基准。结果表明，多语言HuBERT预训练是跨域鲁棒性的主要驱动力，使100M参数模型性能媲美更大规模及商用系统。除误报率（EER）外，本文引入基于扰动的测试时增强协议与随机不确定性分析，揭示标准指标无法捕捉的校准差异：WavLM变体在扰动下表现出过度自信的校准偏差，而迭代式mHuBERT则保持稳定。研究结论指出，SSL预训练轨迹而非模型规模，才是可靠语音深度伪造检测的关键。
原文摘要 · Abstract (English)
Self-supervised learning (SSL) underpins modern audio deepfake detection, yet most prior work centers on a single large wav2vec2-XLSR backbone, leaving compact under studied. We present RAPTOR, Representation Aware Pairwise-gated Transformer for Out-of-domain Recognition a controlled study of compact SSL backbones from the HuBERT and WavLM within a unified pairwise-gated fusion detector, evaluated across 14 cross-domain benchmarks. We show that multilingual HuBERT pre-training is the primary driver of cross-domain robustness, enabling 100M models to match larger and commercial systems. Beyond EER, we introduce a test-time augmentation protocol with perturbation-based aleatoric uncertainty to expose calibration differences invisible to standard metrics: WavLM variants exhibit overconfident miscalibration under perturbation, whereas iterative mHuBERT remains stable. These findings indicate that SSL pre-training trajectory, not model scale, drives reliable audio deepfake detection.
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。