The countermeasure (CM) model is developed to protect Automatic Speaker Verification (ASV) systems from spoof attacks and prevent resulting personal information leakage. Based on practicality and security considerations, the CM model is usually deployed on edge devices, which have more limited computing resources and storage space than cloud-based systems. This work proposes training strategies for a lightweight CM model for ASV, using generalized end-to-end (GE2E) pre-training and adversarial fine-tuning to improve performance, and applying knowledge distillation (KD) to reduce the size of the CM model. In the evaluation phase of the ASVspoof 2021 Logical Access task, the lightweight ResNetSE model reaches min t-DCF 0.2695 and EER 3.54%. Compared to the teacher model, the lightweight student model only uses 22.5% of parameters and 21.1% of multiply and accumulate operands of the teacher model.
翻译:根据实用性和安全考虑,CM模型通常部署在边缘装置上,这些装置的计算资源和储存空间比云基系统更有限,这项工作为ASV的轻量CM模型提出了培训战略,使用一般的端对端(GE2E)前培训和对抗性微调来提高性能,并应用知识蒸馏(KD)来缩小CM模型的规模。在ASVpoof 2021 Local Access任务的评估阶段,轻量式ResNetSE模型达到mt-DCF 0.2695和ER3.54%。与教师模型相比,轻量级学生模型只使用22.5%的参数和21.1%的教师模型的倍数和累积操作量。