Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning

Abstract

In industrial applications, the early detection of malfunctioning factory machinery is crucial. In this paper, we consider acoustic malfunction detection via transfer learning. Contrary to the majority of current approaches which are based on deep autoencoders, we propose to extract features using neural networks that were pretrained on the task of image classification. We then use these features to train a variety of anomaly detection models and show that this improves results compared to convolutional autoencoders in recordings of four different factory machines in noisy environments. Moreover, we find that features extracted from ResNet based networks yield better results than those from AlexNet and Squeezenet. In our setting, Gaussian Mixture Models and One-Class Support Vector Machines achieve the best anomaly detection performance.

ICAART 2021, 8 pages, 2 figures, 1 table

References in corpus (10)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• WaveNet: A Generative Model for Raw Audio
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Densely Connected Convolutional Networks
• A multi-device dataset for urban acoustic scene classification
• musicnn: Pre-trained convolutional neural networks for music audio tagging
• MIMII Dataset: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection
• ToyADMOS: A Dataset of Miniature-Machine Operating Sounds for Anomalous Sound Detection

Cited by in corpus (3)

• Acoustic Leak Detection in Water Networks
• Why do Angular Margin Losses work well for Semi-Supervised Anomalous Sound Detection?
• Regional-Local Adversarially Learned One-Class Classifier Anomalous Sound Detection in Global Long-Term Space