用专家混合模型提升语音欺骗检测的泛化能力
From Self-Supervised Speech Models to Mixture-of-Experts for Robust Anti-Spoofing
- 将自监督语音模型改造成分层门控专家混合架构
- 在14个数据集上将误报率降低至4.81%，相对提升11.9%
- 适合需要鲁棒反欺骗检测的语音安全系统
近年来语音合成技术显著提升了合成语音的自然度，使语音欺骗检测面临更大挑战。当前反欺骗系统的主要局限在于对未见合成方法的鲁棒性不足。本文将自监督语音表示模型改造为多专家（Mixture-of-Experts, MoE）架构，在选定编码器层中用多个专家网络替代前馈模块，并通过分层门控机制控制，使专家能捕捉互补声学特征，同时保留预训练阶段学习到的表示。我们进一步分析了影响该MoE转换性能的结构选择，并研究了专家激活行为。所提方法在14个欺骗检测数据集上评估，宏平均误报率（macro EER）从5.46%降至4.81%，相对基线提升11.9%。
原文摘要 · Abstract (English)
Recent advances in speech generation have significantly improved the naturalness of synthetic speech, making spoofing detection increasingly challenging. A key limitation of current anti-spoofing systems is their limited robustness to unseen synthesis methods. In this work, we transform a self-supervised speech representation model into a Mixture-of-Experts (MoE) architecture to improve generalization. Feed-forward blocks in selected encoder layers are replaced by multiple expert networks controlled by a layer-wise gating mechanism, allowing experts to capture complementary acoustic patterns while preserving the representations learned during self-supervised pretraining. We further analyze the architectural choices affecting the performance of this MoE conversion and investigate the activation behavior of the experts. The proposed approach is evaluated on 14 spoofing datasets and reduces the macro EER from 5.46% to 4.81%, corresponding to 11.9% relative improvement over the baseline.
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。