Analysis of Feature Representations for Anomalous Sound Detection

被引:7
|
作者
Mueller, Robert [1 ]
Illium, Steffen [1 ]
Ritz, Fabian [1 ]
Schmid, Kyrill [1 ]
机构
[1] Ludwig Maximilians Univ Munchen, Mobile & Distributed Syst Grp, Munich, Germany
关键词
Anomaly Detection; Transfer Learning; Machine Health Monitoring;
D O I
10.5220/0010226800970106
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:97 / 106
页数:10
相关论文
共 50 条
  • [21] ANOMALOUS SOUND DETECTION USING ATTENTIVE NEURAL PROCESSES
    Wichern, Gordon
    Chakrabarty, Ankush
    Wang, Zhong-Qiu
    Le Roux, Jonathan
    2021 IEEE WORKSHOP ON APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS (WASPAA), 2021, : 186 - 190
  • [22] Anomalous Sound Detection Framework Based on Masking Strategy
    Li, Xiang
    Zhao, Caidan
    Gao, Chenxing
    Hu, Wenxin
    ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, PT VI, ICIC 2024, 2024, 14880 : 287 - 298
  • [23] Distributed collaborative anomalous sound detection by embedding sharing
    Dohi, Kota
    Kawaguchi, Yohei
    32ND EUROPEAN SIGNAL PROCESSING CONFERENCE, EUSIPCO 2024, 2024, : 91 - 95
  • [24] Deep Convolutional Variational Autoencoder for Anomalous Sound Detection
    Minh-Hieu Nguyen
    Duy-Quang Nguyen
    Dinh-Quoc Nguyen
    Cong-Nguyen Pham
    Dai Bui
    Huy-Dung Han
    IEEE ICCE 2020: 2020 IEEE EIGHTH INTERNATIONAL CONFERENCE ON COMMUNICATIONS AND ELECTRONICS (ICCE), 2021, : 313 - 318
  • [25] Exploring interpretable representations for heart sound abnormality detection
    Wang, Zhihua
    Qian, Kun
    Liu, Houguang
    Hu, Bin
    Schuller, Bjorn W.
    Yamamoto, Yoshiharu
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2023, 82
  • [26] Analysis of feature dependencies in sound description
    Wieczorkowska, AA
    Zytkow, JM
    JOURNAL OF INTELLIGENT INFORMATION SYSTEMS, 2003, 20 (03) : 285 - 302
  • [27] Analysis of Feature Dependencies in Sound Description
    Alicja A. Wieczorkowska
    Jan M. Żytkow
    Journal of Intelligent Information Systems, 2003, 20 : 285 - 302
  • [28] Detection of Anomalous Crowd Behavior Based on the Acceleration Feature
    Chen, Chunyu
    Shao, Yu
    Bi, Xiaojun
    IEEE SENSORS JOURNAL, 2015, 15 (12) : 7252 - 7261
  • [29] Adaptive detection of signals with linear feature mappings and representations
    Yu, XL
    Reed, IS
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1995, 43 (12) : 2953 - 2963
  • [30] A Comprehensive Study of Feature Representations for Semantic Concept Detection
    Duy-Dinh Le
    Satoh, Shin'ichi
    FIFTH IEEE INTERNATIONAL CONFERENCE ON SEMANTIC COMPUTING (ICSC 2011), 2011, : 235 - 238