Explainable anomaly detection for sound spectrograms using pooling statistics with quantile differences

TL;DR

This paper introduces an explainable anomaly detection method for sound spectrograms that uses pooling statistics and quantile differences, suitable for industrial applications requiring transparent AI solutions.

Contribution

The paper presents a novel, statistically motivated anomaly detection approach for spectrograms that offers intrinsic explainability, addressing industrial needs for transparent AI.

Findings

Effective detection of anomalies in sound spectrograms.

Provides interpretable results suitable for industrial use.

Outperforms some existing methods in accuracy and explainability.

Abstract

Anomaly detection is the task of identifying rarely occurring (i.e. anormal or anomalous) samples that differ from almost all other samples in a dataset. As the patterns of anormal samples are usually not known a priori, this task is highly challenging. Consequently, anomaly detection lies between semi- and unsupervised learning. The detection of anomalies in sound data, often called 'ASD' (Anomalous Sound Detection), is a sub-field that deals with the identification of new and yet unknown effects in acoustic recordings. It is of great importance for various applications in Industry 4.0. Here, vibrational or acoustic data are typically obtained from standard sensor signals used for predictive maintenance. Examples cover machine condition monitoring or quality assurance to track the state of components or products. However, the use of intelligent algorithms remains a controversial topic. Management generally aims for cost-reduction and automation, while quality and maintenance experts emphasize the need for human expertise and comprehensible solutions. In this work, we present an anomaly detection approach specifically designed for spectrograms. The approach is based on statistical evaluations and is theoretically motivated. In addition, it features intrinsic explainability, making it particularly suitable for applications in industrial settings. Thus, this algorithm is of relevance for applications in which black-box algorithms are unwanted or unsuitable.