用于自动说话人验证反制模型的对抗性说话人蒸馏
Adversarial Speaker Distillation for Countermeasure Model on Automatic Speaker Verification
AI总结：
针对边缘设备部署 CM 模型时大小与性能的权衡问题，提出结合 GE2E 预训练和对抗性微调的对抗性说话人蒸馏方法，所提 ASD-ResNetSE 模型在 ASVspoof 2021 任务中取得优异性能且参数和计算量大幅减少。
摘要：
反制（CM）模型旨在保护自动说话人验证（ASV）系统免受 spoof 攻击，防止由此导致的个人信息泄露。出于实用性和安全性考虑，CM 模型通常部署在边缘设备上，这类设备的计算资源和存储空间比云系统更有限，因此模型大小受到限制。为更好地权衡 CM 模型的大小与性能，我们提出了一种对抗性说话人蒸馏方法，该方法是结合广义端到端（GE2E）预训练和对抗性微调的知识蒸馏改进版本。在 ASVspoof 2021 Logical Access 任务的评估中，我们提出的对抗性说话人蒸馏 ResNetSE（ASD-ResNetSE）模型达到 0.2695 min t-DCF 和 3.54% EER。ASD-ResNetSE 仅使用 ResNetSE 模型 22.5% 的参数和 19.4% 的乘加操作数。
英文摘要：
The countermeasure (CM) model is developed to protect ASV systems from spoof attacks and prevent resulting personal information leakage in Automatic Speaker Verification (ASV) system. 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, confining the model size under a limitation. To better trade off the CM model sizes and performance, we proposed an adversarial speaker distillation method, which is an improved version of knowledge distillation method combined with generalized end-to-end (GE2E) pre-training and adversarial fine-tuning. In the evaluation phase of the ASVspoof 2021 Logical Access task, our proposed adversarial speaker distillation ResNetSE (ASD-ResNetSE) model reaches 0.2695 min t-DCF and 3.54% EER. ASD-ResNetSE only used 22.5% of parameters and 19.4% of multiply and accumulate operands of ResNetSE model.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
