AI 中文总结
针对伪造语音检测中因新生成模型带来的挑战及持续学习的灾难性遗忘问题，提出在冻结检测器中用域翻译器及回溯翻译器网络的抗遗忘方案，实验显示该方案能高检测率、省计算量并保持对先前数据的检测精度。
AI 中文摘要
新型且更精确的生成模型的发展给伪造语音检测器带来了越来越大的挑战。持续学习技术虽被广泛视为更新模型到新数据集的可行策略，但会导致对先前样本的性能下降（灾难性遗忘）。在这项工作中，我们提出了一种基于在冻结检测器中采用域翻译器的抗遗忘解决方案，通过回溯翻译器网络将新特征空间重新映射到原始空间。实验结果表明，该策略相对于传统再训练能实现高检测率，同时最小化计算量并保持对先前数据的检测精度。
英文摘要
Fake speech detectors are increasingly challenged by the development of new and more accurate generative models. To cope with this problem, continual learning techniques are nowadays widely considered feasible strategies for updating models to new datasets, but they also lead to decreased performance on previously seen samples (catastrophic forgetting). In this work, we propose a forgetting-resilient solution based on the adoption of domain translators within a frozen detector, which remaps the new feature spaces into the original ones by means of a traceback translator network. Experimental results show that this strategy enables the achievement of high detection rates with respect to traditional retraining, while minimizing the computational effort and preserving the detection accuracy on previous data.
CommentsAccepted at EUSIPCO 2026
