First-shot anomaly sound detection for machine condition monitoring: A domain generalization baseline

TL;DR

This paper introduces a baseline system for unsupervised anomaly sound detection in machine condition monitoring that complies with first-shot constraints and demonstrates domain generalization capabilities in the DCASE 2022 and 2023 challenges.

Contribution

It presents a simple autoencoder-based baseline with Mahalanobis metric for first-shot anomaly detection, establishing a benchmark for domain generalization in this task.

Findings

Achieved benchmark performance on DCASE2022 Challenge Task 2

Demonstrated effectiveness of autoencoder with Mahalanobis metric

Provided source code for reproducibility

Abstract

This paper provides a baseline system for First-shot-compliant unsupervised anomaly detection (ASD) for machine condition monitoring. First-shot ASD does not allow systems to do machine-type dependent hyperparameter tuning or tool ensembling based on the performance metric calculated with the grand truth. To show benchmark performance for First-shot ASD, this paper proposes an anomaly sound detection system that works on the domain generalization task in the Detection and Classification of Acoustic Scenes and Events (DCASE) 2022 Challenge Task 2: "Unsupervised Anomalous Sound Detection for Machine Condition Monitoring Applying Domain Generalization Technique" while complying with the First-shot requirements introduced in the DCASE 2023 Challenge Task 2 (DCASE2023T2). A simple autoencoder based implementation combined with selective Mahalanobis metric is implemented as a baseline system. The performance evaluation is conducted to set the target benchmark for the forthcoming DCASE2023T2. Source code of the baseline system will be available on GitHub: https://github.com/nttcslab/dcase2023_task2_baseline_ae .