MoE让反欺骗更强，EER降11.9%
语音生成技术的进步使合成语音越来越自然，导致欺骗检测更加困难。本研究将自监督语音表示模型转换为混合专家（MoE）架构，替换编码器层的前馈块为多个专家网络，并通过层间门控机制控制专家激活。专家网络能捕获互补的声学模式，同时保留自监督预训练学到的表示。在14个欺骗数据集上的评估显示，宏等错误率（EER）从5.46%降至4.81%，相对提升11.9%。
From Self-Supervised Speech Models to Mixture-of-Experts for Robust Anti-Spoofing
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.