Activity-Guided Industrial Anomalous Sound Detection against Interferences
This addresses the problem of robust anomaly detection in noisy industrial environments for maintenance and monitoring applications, representing an incremental improvement by integrating activity information into existing methods.
The paper tackles anomaly detection for industrial sound data corrupted by background noise and interference from neighboring machines, proposing SSAD, a framework that uses machine activity information to separate sources and detect anomalies, achieving comparable accuracy to a baseline with clean signals and outperforming standard approaches in interference cases.
We address a practical scenario of anomaly detection for industrial sound data, where the sound of a target machine is corrupted by background noise and interference from neighboring machines. Overcoming this challenge is difficult since the interference is often virtually indistinguishable from the target machine without additional information. To address the issue, we propose SSAD, a framework of source separation (SS) followed by anomaly detection (AD), which leverages machine activity information, often readily available in practical settings. SSAD consists of two components: (i) activity-informed SS, enabling effective source separation even given interference with similar timbre, and (ii) two-step masking, robustifying anomaly detection by emphasizing anomalies aligned with the machine activity. Our experiments demonstrate that SSAD achieves comparable accuracy to a baseline with full access to clean signals, while SSAD is provided only a corrupted signal and activity information. In addition, thanks to the activity-informed SS and AD with the two-step masking, SSAD outperforms standard approaches, particularly in cases with interference. It highlights the practical efficacy of SSAD in addressing the complexities of anomaly detection in industrial sound data.