Deep Dense and Convolutional Autoencoders for Unsupervised Anomaly Detection in Machine Condition Sounds
This work addresses anomaly detection for machine maintenance, but it is incremental as it applies existing autoencoder methods to a specific challenge task.
The authors tackled unsupervised anomaly detection in machine condition sounds using deep autoencoders, achieving competitive results that outperformed the baseline method on six machine type datasets from the DCASE 2020 challenge.
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.