Automatic detection of machine anomaly remains challenging for machine learning. We believe the capability of generative adversarial network (GAN) suits the need of machine audio anomaly detection, yet rarely has this been investigated by previous work. In this paper, we propose AEGAN-AD, a totally unsupervised approach in which the generator (also an autoencoder) is trained to reconstruct input spectrograms. It is pointed out that the denoising nature of reconstruction deprecates its capacity. Thus, the discriminator is redesigned to aid the generator during both training stage and detection stage. The performance of AEGAN-AD on the dataset of DCASE 2022 Challenge TASK 2 demonstrates the state-of-the-art result on five machine types. A novel anomaly localization method is also investigated. Source code available at: www.github.com/jianganbai/AEGAN-AD

翻译：机器异常自动检测对机器学习仍具挑战性。我们认为生成对抗网络（GAN）的能力契合机器音频异常检测的需求，但此前研究鲜有涉足。本文提出AEGAN-AD，一种完全无监督的方法，其中生成器（亦为自编码器）被训练用于重构输入频谱图。本文指出，重构的去噪特性削弱了其检测能力。因此，判别器被重新设计，以在训练阶段和检测阶段辅助生成器。AEGAN-AD在DCASE 2022挑战赛任务2数据集上的表现展示了其在五种机器类型上的最先进结果。此外，本文还研究了一种新颖的异常定位方法。源代码可见：www.github.com/jianganbai/AEGAN-AD