Serial-OE: Anomalous sound detection based on serial method with outlier exposure capable of using small amounts of anomalous data for training

TL;DR

Serial-OE introduces an anomalous sound detection method that effectively utilizes small amounts of anomalous data and outlier exposure to enhance detection accuracy, outperforming existing models on benchmark datasets.

Contribution

It presents a novel outlier exposure framework that incorporates limited anomalous data into training, improving ASD performance over traditional normal-data-only models.

Findings

Outperforms state-of-the-art ASD models on DCASE2020 dataset

Effective with small amounts of anomalous data during training

Robust to data contamination and absence of machine ID information

Abstract

We introduce Serial-OE, a new approach to anomalous sound detection (ASD) that leverages small amounts of anomalous data to improve the performance. Conventional ASD methods rely primarily on the modeling of normal data, due to the cost of collecting anomalous data from various possible types of equipment breakdowns. Our method improves upon existing ASD systems by implementing an outlier exposure framework that utilizes normal and pseudo-anomalous data for training, with the capability to also use small amounts of real anomalous data. A comprehensive evaluation using the DCASE2020 Task2 dataset shows that our method outperforms state-of-the-art ASD models. We also investigate the impact on performance of using a small amount of anomalous data during training, of using data without machine ID information, and of using contaminated training data. Our experimental results reveal the potential of using a very limited amount of anomalous data during training to address the limitations of existing methods using only normal data for training due to the scarcity of anomalous data. This study contributes to the field by presenting a method that can be dynamically adapted to include anomalous data during the operational phase of an ASD system, paving the way for more accurate ASD.