Analysis of Feature Representations for Anomalous Sound Detection

Robert Müller, Steffen Illium, Fabian Ritz, Kyrill Schmid

2021

Abstract

In this work, we thoroughly evaluate the efficacy of pretrained neural networks as feature extractors for anomalous sound detection. In doing so, we leverage the knowledge that is contained in these neural networks to extract semantically rich features (representations) that serve as input to a Gaussian Mixture Model which is used as a density estimator to model normality. We compare feature extractors that were trained on data from various domains, namely: images, environmental sounds and music. Our approach is evaluated on recordings from factory machinery such as valves, pumps, sliders and fans. All of the evaluated representations outperform the autoencoder baseline with music based representations yielding the best performance in most cases. These results challenge the common assumption that closely matching the domain of the feature extractor and the downstream task results in better downstream task performance.

Download


Paper Citation


in Harvard Style

Müller R., Illium S., Ritz F. and Schmid K. (2021). Analysis of Feature Representations for Anomalous Sound Detection.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-484-8, pages 97-106. DOI: 10.5220/0010226800970106


in Bibtex Style

@conference{icaart21,
author={Robert Müller and Steffen Illium and Fabian Ritz and Kyrill Schmid},
title={Analysis of Feature Representations for Anomalous Sound Detection},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2021},
pages={97-106},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010226800970106},
isbn={978-989-758-484-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Analysis of Feature Representations for Anomalous Sound Detection
SN - 978-989-758-484-8
AU - Müller R.
AU - Illium S.
AU - Ritz F.
AU - Schmid K.
PY - 2021
SP - 97
EP - 106
DO - 10.5220/0010226800970106