ASD-Diffusion: Anomalous Sound Detection with Diffusion Models
This addresses anomaly detection in industrial acoustic monitoring, representing an incremental advancement by applying diffusion models to this domain.
The paper tackles unsupervised anomalous sound detection in factory environments by proposing ASD-Diffusion, which reconstructs anomalous acoustic features to normal patterns using diffusion models and includes a post-processing filter. Experimental results show a 7.75% improvement over the baseline on the DCASE 2023 challenge dataset.
Unsupervised Anomalous Sound Detection (ASD) aims to design a generalizable method that can be used to detect anomalies when only normal sounds are given. In this paper, Anomalous Sound Detection based on Diffusion Models (ASD-Diffusion) is proposed for ASD in real-world factories. In our pipeline, the anomalies in acoustic features are reconstructed from their noisy corrupted features into their approximate normal pattern. Secondly, a post-processing anomalies filter algorithm is proposed to detect anomalies that exhibit significant deviation from the original input after reconstruction. Furthermore, denoising diffusion implicit model is introduced to accelerate the inference speed by a longer sampling interval of the denoising process. The proposed method is innovative in the application of diffusion models as a new scheme. Experimental results on the development set of DCASE 2023 challenge task 2 outperform the baseline by 7.75%, demonstrating the effectiveness of the proposed method.