Acoustic anomaly detection via latent regularized gaussian mixture generative adversarial networks

2020/02/04 by Cheng‐Wei Chen, Pan Chen, Chen, Chengwei +11
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Audio and Speech Processing (eess.AS) #Computer Vision and Pattern Recognition (cs.CV) #Digital Media Forensic Detection #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Sound (cs.SD) #Water Systems and Optimization #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2002.01107

openalex publication_date 2020/02/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Acoustic anomaly detection aims at distinguishing abnormal acoustic signals from the normal ones. It suffers from the class imbalance issue and the lacking in the abnormal instances. In addition, collecting all kinds of abnormal or unknown samples for training purpose is impractical and timeconsuming. In this paper, a novel Gaussian Mixture Generative Adversarial Network (GMGAN) is proposed under semi-supervised learning framework, in which the underlying structure of training data is not only captured in spectrogram reconstruction space, but also can be further restricted in the space of latent representation in a discriminant manner. Experiments show that our model has clear superiority over previous methods, and achieves the state-of-the-art results on DCASE dataset.

Citations

• On Estimation of a Probability Density Function and Mode

Related

• Unsupervised Anomaly Detection and Localization of Machine Audio: A GAN-based Approach
• Deep Autoencoding GMM-based Unsupervised Anomaly Detection in Acoustic Signals and its Hyper-parameter Optimization
• Anomaly Detection by One Class Latent Regularized Networks
• Representational learning for an anomalous sound detection system with source separation model
• MDGAN: Boosting Anomaly Detection Using Multi-Discriminator Generative Adversarial Networks