English

Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning

Audio and Speech Processing 2021-02-19 v2 Computer Vision and Pattern Recognition Machine Learning Sound

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.

Keywords

Cite

@article{arxiv.2006.03429,
  title  = {Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning},
  author = {Robert Müller and Fabian Ritz and Steffen Illium and Claudia Linnhoff-Popien},
  journal= {arXiv preprint arXiv:2006.03429},
  year   = {2021}
}

Comments

ICAART 2021, 8 pages, 2 figures, 1 table

R2 v1 2026-06-23T16:05:22.245Z