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
  • [31] An auditory feature detection circuit for sound pattern recognition
    Schoeneich, Stefan
    Kostarakos, Konstantinos
    Hedwig, Berthold
    SCIENCE ADVANCES, 2015, 1 (08):
  • [32] ANOMALOUS SOUND DETECTION BASED ON INTERPOLATION DEEP NEURAL NETWORK
    Suefusa, Kaori
    Nishida, Tomoya
    Purohit, Harsh
    Tanabe, Ryo
    Endo, Takashi
    Kawaguchi, Yohei
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 271 - 275
  • [33] Enhanced Feature Extraction Approaches for Detection of Sound Events
    Surampudi, Naren
    Srirangan, M.
    Christopher, Jabez
    PROCEEDINGS OF THE 2019 IEEE 9TH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTING (IACC 2019), 2019, : 223 - 229
  • [34] ANOMALY DETECTION BASED ON AN ENSEMBLE OF DEREVERBERATION AND ANOMALOUS SOUND EXTRACTION
    Kawaguchi, Yohei
    Tanabe, Ryo
    Endo, Takashi
    Ichige, Kenji
    Hamada, Koichi
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 865 - 869
  • [35] An Efficient Anomalous Sound Detection by Robust Processing and Reformation of Objective
    Tsai, Tsung-Lin
    Lo, Yi-Cheng
    Wu, An-Yeu
    2024 IEEE 6TH INTERNATIONAL CONFERENCE ON AI CIRCUITS AND SYSTEMS, AICAS 2024, 2024, : 268 - 272
  • [36] Advanced Anomaly Detection in Manufacturing Processes: Leveraging Feature Value Analysis for Normalizing Anomalous Data
    Kim, Seunghyun
    Seo, Hyunsoo
    Lee, Eui Chul
    ELECTRONICS, 2024, 13 (07)
  • [37] Anomalous Sound Detection Using Self-Attention-Based Frequency Pattern Analysis of Machine Sounds
    Zhang, Hejing
    Guan, Jian
    Zhu, Qiaoxi
    Xiao, Feiyang
    Liu, Youde
    INTERSPEECH 2023, 2023, : 336 - 340
  • [38] New tracheal sound feature for apnoea analysis
    Kulkas, A.
    Huupponen, E.
    Virkkala, J.
    Tenhunen, M.
    Saastamoinen, A.
    Rauhala, E.
    Himanen, S. -L.
    MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 2009, 47 (04) : 405 - 412
  • [39] A Novel Approach for Trajectory Feature Representation and Anomalous Trajectory Detection
    Feng, Wenhui
    Han, Chongzhao
    2015 18TH INTERNATIONAL CONFERENCE ON INFORMATION FUSION (FUSION), 2015, : 1093 - 1099
  • [40] New tracheal sound feature for apnoea analysis
    A. Kulkas
    E. Huupponen
    J. Virkkala
    M. Tenhunen
    A. Saastamoinen
    E. Rauhala
    S.-L. Himanen
    Medical & Biological Engineering & Computing, 2009, 47 : 405 - 412