Hierarchical Conditional Variational Autoencoder Based Acoustic Anomaly Detection

TL;DR

This paper introduces a hierarchical conditional variational autoencoder (HCVAE) for unsupervised acoustic anomaly detection in machines, leveraging hierarchical knowledge to improve latent space representation and generalization across machine types.

Contribution

The paper proposes HCVAE, a novel model that incorporates hierarchical knowledge to enhance anomaly detection and generalize across different machines with a single model.

Findings

HCVAE outperforms baseline by up to 15% in AUC score.

HCVAE generalizes well across different machine types.

Partial hierarchical knowledge still improves detection performance.

Abstract

This paper aims to develop an acoustic signal-based unsupervised anomaly detection method for automatic machine monitoring. Existing approaches such as deep autoencoder (DAE), variational autoencoder (VAE), conditional variational autoencoder (CVAE) etc. have limited representation capabilities in the latent space and, hence, poor anomaly detection performance. Different models have to be trained for each different kind of machines to accurately perform the anomaly detection task. To solve this issue, we propose a new method named as hierarchical conditional variational autoencoder (HCVAE). This method utilizes available taxonomic hierarchical knowledge about industrial facility to refine the latent space representation. This knowledge helps model to improve the anomaly detection performance as well. We demonstrated the generalization capability of a single HCVAE model for different types of machines by using appropriate conditions. Additionally, to show the practicability of the proposed approach, (i) we evaluated HCVAE model on different domain and (ii) we checked the effect of partial hierarchical knowledge. Our results show that HCVAE method validates both of these points, and it outperforms the baseline system on anomaly detection task by utmost 15 % on the AUC score metric.