Representational learning for an anomalous sound detection system with source separation model

TL;DR

This paper introduces a novel source separation-based training method for anomalous sound detection that improves performance by leveraging diverse machine sounds and enhances representation learning with limited data.

Contribution

The paper proposes a source separation model (CMGAN) approach for training anomalous sound detection systems, overcoming limitations of auto-encoders and auxiliary tasks.

Findings

Proposed method outperforms conventional auto-encoder and source separation approaches.

Enhanced representation learning with increased non-target data.

Effective training with limited target class samples.

Abstract

The detection of anomalous sounds in machinery operation presents a significant challenge due to the difficulty in generalizing anomalous acoustic patterns. This task is typically approached as an unsupervised learning or novelty detection problem, given the complexities associated with the acquisition of comprehensive anomalous acoustic data. Conventional methodologies for training anomalous sound detection systems primarily employ auto-encoder architectures or representational learning with auxiliary tasks. However, both approaches have inherent limitations. Auto-encoder structures are constrained to utilizing only the target machine's operational sounds, while training with auxiliary tasks, although capable of incorporating diverse acoustic inputs, may yield representations that lack correlation with the characteristic acoustic signatures of anomalous conditions. We propose a training method based on the source separation model (CMGAN) that aims to isolate non-target machine sounds from a mixture of target and non-target class acoustic signals. This approach enables the effective utilization of diverse machine sounds and facilitates the training of complex neural network architectures with limited sample sizes. Our experimental results demonstrate that the proposed method yields better performance compared to both conventional auto-encoder training approaches and source separation techniques that focus on isolating target machine signals. Moreover, our experimental results demonstrate that the proposed method exhibits the potential for enhanced representation learning as the quantity of non-target data increases, even while maintaining a constant volume of target class data.