How Much Does Machine Identity Matter in Anomalous Sound Detection at Test Time?
For practitioners deploying ASD in multi-machine environments, this work highlights the need for methods robust to unknown machine identity, as current benchmarks overestimate real-world performance.
The paper investigates the impact of unknown machine identity on anomalous sound detection (ASD) performance, showing that relaxing the assumption of known machine identity at test time reveals significant performance degradations (e.g., up to 20% drop in AUC) and method-specific robustness differences that are hidden under standard machine-wise evaluation.
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.