How Much Does Machine Identity Matter in Anomalous Sound Detection at Test Time?

TL;DR

This paper investigates how the assumption of known machine identity affects anomalous sound detection performance, revealing that removing this assumption exposes robustness issues and performance degradations.

Contribution

It introduces a modified evaluation protocol for ASD that does not rely on machine identity, highlighting robustness challenges in more realistic scenarios.

Findings

Performance degrades when machine identity is unknown at test time.

Method-specific robustness differences become evident under the new evaluation protocol.

Degradations are strongly linked to implicit machine identification accuracy.

Abstract

Anomalous sound detection (ASD) benchmarks typically assume that the identity of the monitored machine is known at test time and that recordings are evaluated in a machine-wise manner. However, in realistic monitoring scenarios with multiple known machines operating concurrently, test recordings may not be reliably attributable to a specific machine, and requiring machine identity imposes deployment constraints such as dedicated sensors per machine. To reveal performance degradations and method-specific differences in robustness that are hidden under standard machine-wise evaluation, we consider a minimal modification of the ASD evaluation protocol in which test recordings from multiple machines are merged and evaluated jointly without access to machine identity at inference time. Training data and evaluation metrics remain unchanged, and machine identity labels are used only for post hoc evaluation. Experiments with representative ASD methods show that relaxing this assumption reveals performance degradations and method-specific differences in robustness that are hidden under standard machine-wise evaluation, and that these degradations are strongly related to implicit machine identification accuracy.