Deep Dense and Convolutional Autoencoders for Unsupervised Anomaly Detection in Machine Condition Sounds

TL;DR

This paper presents two deep autoencoder-based methods using dense and convolutional architectures for unsupervised anomaly detection in machine sounds, demonstrating superior performance on challenge datasets.

Contribution

Introduction of dense and convolutional autoencoder models for unsupervised anomaly detection in machine condition sounds, advancing previous baseline methods.

Findings

Autoencoders outperform baseline methods.

Convolutional autoencoders achieve higher accuracy.

Methods are effective across multiple machine types.

Abstract

This technical report describes two methods that were developed for Task 2 of the DCASE 2020 challenge. The challenge involves an unsupervised learning to detect anomalous sounds, thus only normal machine working condition samples are available during the training process. The two methods involve deep autoencoders, based on dense and convolutional architectures that use melspectogram processed sound features. Experiments were held, using the six machine type datasets of the challenge. Overall, competitive results were achieved by the proposed dense and convolutional AE, outperforming the baseline challenge method.