Analysis of Feature Representations for Anomalous Sound Detection

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 Gaus...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Müller, Robert, Illium, Steffen, Ritz, Fabian, Schmid, Kyrill
Format Paper Journal Article
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 11.12.2020
Subjects
Acoustics
Background noise
Computer Science - Learning
Computer Science - Sound
Domains
Downstream effects
Feature extraction
Music
Neural networks
Probabilistic models
Representations
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422
DOI:10.48550/arxiv.2012.06282