Detecting Replay Attacks Using Multi-Channel Audio: A Neural Network-Based Method
Detecting Replay Attacks Using Multi-Channel Audio: A Neural Network-Based Method
复制标题
DOI：
10.1109/lsp.2020.2996908
复制
发表时间：
2020-01-01
影响因子：
3.9
通讯作者：
Poellabauer, Christian
中科院分区：
文献类型：
--
作者：
Gong, Yuan;Yang, Jian;Poellabauer, Christian
随着使用语音作为主要输入的安全敏感系统的数量迅速增长，解决这些系统对重放攻击的潜在脆弱性变得越来越重要。以前解决这一问题的努力主要集中在单声道音频上。在本文中，我们介绍了一种新的基于神经网络的重放攻击检测模型，进一步利用多声道音频的空间信息，并能够显着提高重放攻击检测性能。
With the rapidly growing number of security-sensitive systems that use voice as the primary input, it becomes increasingly important to address these systems' potential vulnerability to replay attacks. Previous efforts to address this concern have focused primarily on single-channel audio. In this paper, we introduce a novel neural network-based replay attack detection model that further leverages spatial information of multi-channel audio and is able to significantly improve the replay attack detection performance.