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
  • [41] Deep graph clustering with enhanced feature representations for community detection
    Hao, Jie
    Zhu, William
    APPLIED INTELLIGENCE, 2023, 53 (02) : 1336 - 1349
  • [42] Empirical Evaluation of Different Feature Representations for Social Circles Detection
    Alonso, Jesus
    Paredes, Roberto
    Rosso, Paolo
    PATTERN RECOGNITION AND IMAGE ANALYSIS (IBPRIA 2015), 2015, 9117 : 31 - 38
  • [43] Deep graph clustering with enhanced feature representations for community detection
    Jie Hao
    William Zhu
    Applied Intelligence, 2023, 53 : 1336 - 1349
  • [44] A comparison of system call feature representations for insider threat detection
    Liu, A
    Martin, C
    Hetherington, T
    Matzner, S
    PROCEEDINGS FROM THE SIXTH ANNUAL IEEE SYSTEMS, MAN AND CYBERNETICS INFORMATION ASSURANCE WORKSHOP, 2005, : 340 - 347
  • [45] GRAPHIC REPRESENTATIONS OF SOUND: A TOOL FOR THE ANALYSIS OF PIANO PERFORMANCE
    Lorenzo Gracia, Ruben
    ANUARIO MUSICAL, 2010, (65) : 197 - 224
  • [46] Sound-Event Partitioning and Feature Normalization for Robust Sound-Event Detection
    Lei, Baiying
    Mak, Man-Wai
    2014 19TH INTERNATIONAL CONFERENCE ON DIGITAL SIGNAL PROCESSING (DSP), 2014, : 389 - 394
  • [47] A study on anomalous sound detection in factories for early failure detection using wavelet transform
    Ueda, Masaya
    Tanaka, Daisuke
    Tanaka, Mikiko Sode
    2024 11TH INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS-TAIWAN, ICCE-TAIWAN 2024, 2024, : 469 - 470
  • [48] Locally Masked Convolutional Models for Anomalous Sound Detection by Deep Learning
    Abad, Frederic
    Nakano, Yuta
    Bendahan, Remy
    Takabe, Akiyoshi
    Muneto, Toshiki
    Ito, Hidehiro
    5TH INTERNATIONAL CONFERENCE ON INDUSTRY 4.0 AND SMART MANUFACTURING, ISM 2023, 2024, 232 : 3013 - 3023
  • [49] Variational Classifier for Unsupervised Anomalous Sound Detection under Domain Generalization
    Almudevar, Antonio
    Ortega, Alfonso
    Vicente, Luis
    Miguel, Antonio
    Lleida, Eduardo
    INTERSPEECH 2023, 2023, : 2823 - 2827
  • [50] Unsupervised Anomalous Sound Detection Using Hybrid Machine Learning Techniques
    Yun, Eunsun
    Jeong, Minjoong
    2024 IEEE INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING, IEEE BIGCOMP 2024, 2024, : 347 - 348