Flow-based Self-supervised Density Estimation for Anomalous Sound Detection

TL;DR

This paper introduces a self-supervised density estimation method using flow-based models to improve anomalous sound detection by better distinguishing target machine sounds from others.

Contribution

It proposes a novel training approach that encourages flow models to assign higher likelihoods to target sounds, enhancing out-of-distribution detection capabilities.

Findings

Improved AUC by 4.6% with MAF

Improved AUC by 5.8% with Glow

Significant performance boost over previous methods

Abstract

To develop a machine sound monitoring system, a method for detecting anomalous sound is proposed. Exact likelihood estimation using Normalizing Flows is a promising technique for unsupervised anomaly detection, but it can fail at out-of-distribution detection since the likelihood is affected by the smoothness of the data. To improve the detection performance, we train the model to assign higher likelihood to target machine sounds and lower likelihood to sounds from other machines of the same machine type. We demonstrate that this enables the model to incorporate a self-supervised classification-based approach. Experiments conducted using the DCASE 2020 Challenge Task2 dataset showed that the proposed method improves the AUC by 4.6% on average when using Masked Autoregressive Flow (MAF) and by 5.8% when using Glow, which is a significant improvement over the previous method.