MIMII DG: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection for Domain Generalization Task

TL;DR

This paper introduces MIMII DG, a novel sound dataset designed to evaluate domain generalization methods for anomalous sound detection in industrial machines, addressing the challenge of unseen domain shifts.

Contribution

It provides the first dataset specifically for benchmarking domain generalization techniques in anomalous sound detection, including diverse domain shift scenarios and challenging background noise conditions.

Findings

Baseline experiments show the dataset effectively reproduces domain shifts.

The dataset is useful for benchmarking domain generalization techniques.

It highlights the difficulty of detecting certain domain shifts.

Abstract

We present a machine sound dataset to benchmark domain generalization techniques for anomalous sound detection (ASD). Domain shifts are differences in data distributions that can degrade the detection performance, and handling them is a major issue for the application of ASD systems. While currently available datasets for ASD tasks assume that occurrences of domain shifts are known, in practice, they can be difficult to detect. To handle such domain shifts, domain generalization techniques that perform well regardless of the domains should be investigated. In this paper, we present the first ASD dataset for the domain generalization techniques, called MIMII DG. The dataset consists of five machine types and three domain shift scenarios for each machine type. The dataset is dedicated to the domain generalization task with features such as multiple different values for parameters that cause domain shifts and introduction of domain shifts that can be difficult to detect, such as shifts in the background noise. Experimental results using two baseline systems indicate that the dataset reproduces domain shift scenarios and is useful for benchmarking domain generalization techniques.