Correlation-Based Filtering for Unsupervised Anomalous Sound Detection
Loading...
Author
Bürli, Andrin
Hamdan, Sami
Kastanis, Iason
DOI
Abstract
Unsupervised anomalous sound detection (ASD) under domain shift remains a key challenge for real-world deployment. We introduce a two-stage “first-shot” pipeline for DCASE 2025 Task 2 that leverages optional clean-only or noise-only supplemental recordings to improve robustness to unseen background noises. First, a correlationbased filter is trained separately on clean or noise data, separating each test mixture x = C + N + A into a cleaner signal x′ = C + A. Second, a mel-spectrogram autoencoder, augmented with SMOTE and mixup on x′,detects anomalies. On the development set, our method achieves a high SI-SDR for the separation task and improves the detection metrics for three out of seven components compared to the baseline. These results validate that assuming statistical independence between machine sound,background noise, and anomalies can enhance first-shot ASD. Future work will explore automated correlation estimation and integration with more advanced anomaly detection methods for the second stage
Publication Reference
Bürli, Andrin; Hamdan, Sami; Kastanis, Iason. “Correlation-Based Filtering for Unsupervised Anomalous Sound Detection.” In Proceedings of the 10th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2025), Barcelona, Spain, October 30–31, 2025, pages 11–14.
Year
2025-10-30