Unsupervised Anomaly Detection and Localization of Machine Audio: A GAN-based Approach

Anbai Jiang, Wei-Qiang Zhang, Yufeng Deng, Pingyi Fan, Jia Liu
3/31/2023
cs.SDcs.LGeess.AS

No official code found. Best implementation: jianganbai/AEGAN-AD (52 stars, Apache-2.0, last commit 2025-06-23).

Abstract

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

View on arXivView PDF

Code Implementations(1)

jianganbai/AEGAN-ADCommunity100%
Apache-2.0

Official pytorch implementation of AEGAN-AD

529PythonJan 23, 20231 years agoApache-2.0

Similar Papers

TLDiffGAN: A Latent Diffusion-GAN Framework with Temporal Information Fusion for Anomalous Sound Detection

83% match2026

From Vision to Sound: Advancing Audio Anomaly Detection with Vision-Based Algorithms

82% match2025

MIMII-Gen: Generative Modeling Approach for Simulated Evaluation of Anomalous Sound Detection System

82% match2024

MIMII-Agent: Leveraging LLMs with Function Calling for Relative Evaluation of Anomalous Sound Detection

82% match2025

EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks

82% match2024

Description and Discussion on DCASE 2024 Challenge Task 2: First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring

82% match2024

Cite this paper

@article{jiang2023unsupervised,
  title  = {Unsupervised Anomaly Detection and Localization of Machine Audio: A GAN-based Approach},
  author = {Anbai Jiang and Wei-Qiang Zhang and Yufeng Deng and Pingyi Fan and Jia Liu},
  year   = {2023},
  eprint = {2303.17949},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.17949v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.17949.svg)](https://codeofpaper.com/paper/2303.17949)

Discussion