2022/04/15 by Tomoya Nishida, Kota Dohi, Nishida, Tomoya +7 · 1 citation
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Audio and Speech Processing (eess.AS) #Currency Recognition and Detection #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Sound (cs.SD) #Water Systems and Optimization #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2204.07353
openalex publication_date 2022/04/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We have developed an unsupervised anomalous sound detection method for machine condition monitoring that utilizes an auxiliary task -- detecting when the target machine is active. First, we train a model that detects machine activity by using normal data with machine activity labels and then use the activity-detection error as the anomaly score for a given sound clip if we have access to the ground-truth activity labels in the inference phase. If these labels are not available, the anomaly score is calculated through outlier detection on the embedding vectors obtained by the activity-detection model. Solving this auxiliary task enables the model to learn the difference between the target machine sounds and similar background noise, which makes it possible to identify small deviations in the target sounds. Experimental results showed that the proposed method improves the anomaly-detection performance of the conventional method complementarily by means of an ensemble.