Unsupervised Anomalous Sound Detection for Machine Condition Monitoring Using Classification-Based Methods
Source abstract
Abstract
The task of unsupervised anomalous sound detection (ASD) is challenging for detecting anomalous sounds from a large audio database without any annotated anomalous training data. Many unsupervised methods were proposed, but previous works have confirmed that the classification-based models far exceeds the unsupervised models in ASD. In this paper, we adopt two classification-based anomaly detection models: (1) Outlier classifier is to distinguish anomalous sounds or outliers from the normal; (2) ID classifier identifies anomalies using both the confidence of classification and the similarity of hidden embeddings. We conduct experiments in task 2 of DCASE 2020 challenge, and our ensemble method achieves an averaged area under the curve (AUC) of 95.82% and averaged partial AUC (pAUC) of 92.32%, which outperforms the state-of-the-art models.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Music and Audio Processing · Anomaly Detection Techniques and Applications · Water Systems and Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China
State Grid Xinjiang Electric Power Company, Urumqi 830092, China
References (24)
Show source-provided references
1. Audio Surveillance of Roads: A System for Detecting Anomalous Sounds
2. Probabilistic Novelty Detection for Acoustic Surveillance Under Real-World Conditions10.1109/TMM.2011.2122247 ↗
3. Koizumi, Y., Saito, S., Uematsu, H., and Harada, N. (September, January 28). Optimizing Acoustic Feature Extractor for Anomalous Sound Detection Based on NeymanPearson Lemma. Proceedings of the 2017 25th European Signal Processing Conference (EUSIPCO), Kos, Greece.10.23919/EUSIPCO.2017.8081297 ↗
4. A CRNN System for Sound Event Detection Based on Gastrointestinal Sound Dataset Collected by Wearable Auscultation Devices10.1109/ACCESS.2020.3020099 ↗
5. Ick, C., and Mcfee, B. (2021). Sound Event Detection in Urban Audio With Single and Multi-Rate PCEN. arXiv.10.1109/ICASSP39728.2021.9414697 ↗
6. Koizumi, Y., Kawaguchi, Y., Imoto, K., Nakamura, T., Nikaido, Y., Tanabe, R., Purohit, H., Suefusa, K., Endo, T., and Yasuda, M. (2020). Description and discussion on DCASE2020 challenge task2: Unsupervised anomalous sound detection for machine condition monitoring. arXiv.
7. Koizumi, Y., Saito, S., Uematsu, H., Harada, N., and Imoto, K. (2019, January 20–23). ToyADMOS: A dataset of miniature-machine operating sounds for anomalous sound detection. Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY, USA.10.1109/WASPAA.2019.8937164 ↗
8. Purohit, H., Tanabe, R., Ichige, T., Endo, T., Nikaido, Y., Suefusa, K., and Kawaguchi, Y. (2019, January 20). MIMII Dataset: Sound dataset for malfunctioning industrial machine investigation and inspection. Proceedings of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019), Tokyo, Japan.10.33682/m76f-d618 ↗
9. Hayashi, T., Toshimura, T., and Adachi, Y. (2020). Conformer-Based ID-Aware Autoencoder for Unsupervised Anomalous Sound Detection, Detection and Classification of Acoustic Scenes and Events. Tech. Report in DCASE2020 Challenge Task 2.
10. Wilkinghoff, H. (2020). Anomalous Sound Detection with Look, Listen, and Learn Embeddings, Detection and Classification of Acoustic Scenes and Events. Tech. Report in DCASE2020 Challenge Task 2.
11. Durkota, K., Linda, M., Ludvik, M., and Tozicka, J. (2020). Euron-Net: Siamese Network for Anomaly Detection, Detection and Classification of Acoustic Scenes and Events. Tech. Report in DCASE2020 Challenge Task 2.
12. Haunschmid, V., and Praher, P. (2020). Anomalous Sound Detection with Masked Autoregressive Flows and Machine Type Dependent Postprocessing, Detection and Classification of Acoustic Scenes and Events 2020. Tech. Report in DCASE2020 Challenge Task 2.
13. Giri, R., Tenneti, S.V., Cheng, F., Helwani, K., Isik, U., and Krishnaswamy, A. (2020). Unsupervised Anomalous sound Detection Using Self-Supervised Classification and Group Masked Autoencoder for Density Estimation, Detection and Classification of Acoustic Scenes and Events. Tech. Report in DCASE2020 Challenge Task 2.
14. Daniluk, P., Goździewski, M., Kapka, S., and Kośmider, M. (2020). Ensemble of Auto-Encoder Based and WaveNet Like Systems for Unsupervised Anomaly Detection, Detection and Classification of Acoustic Scenes and Events. Tech. Report in DCASE2020 Challenge Task 2.
15. Primus, P. (2020). Reframing Unsupervised Machine Condition Monitoring as a Supervised Classification Task with Outlier Exposed Classifiers, Detection and Classification of Acoustic Scenes and Events. Tech. Report in DCASE2020 Challenge Task 2.
16. Inoue, T., Vinayavekhin, P., Morikuni, S., Wang, S., Trong, T.H., Wood, D., Tatsubori, M., and Tachibana, R. (2020). Detection of Anomalous Sounds for Machine Condition Monitoring Using Classification Confidence, Detection and Classification of Acoustic Scenes and Events. Tech. Report in DCASE2020 Challenge Task 2.
17. Zhou, Q. (2020). ArcFace Based Sound MobileNets for DCASE 2020 Task 2, Detection and Classification of Acoustic Scenes and Events. Tech. Report in DCASE2020 Challenge Task 2.
18. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
19. Chen, S., Liu, Y., Gao, X., and Han, Z. (2018, January 11–12). MobileFaceNets: Efficient CNNs for accurate realTime face verification on mobile devices. Proceedings of the 13th Chinese Conference, CCBR 2018, Urumqi, China.10.1007/978-3-319-97909-0_46 ↗
20. Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for MobileNetV3. Proceedings of the International Conference on Computer Vision 2019 (ICCV2019), Seoul, Koren.10.1109/ICCV.2019.00140 ↗
21. Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8–14). CBAM: Convolutional Block Attention Module. Proceedings of the 15th European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
22. McFee, B., Raffel, C., Liang, D., Ellis, D.P.W., McVicar, M., Battenberg, E., and Nieto, O. (2015, January 6–12). Librosa: Audio and Music Signal Analysis in Python. Proceedings of the 14th Python in Science Conference, New York, NY, USA.10.25080/Majora-7b98e3ed-003 ↗
23. Loshchilov, I., and Hutter, F. (2016). SGDR: Stochastic gradient descent with warm restarts. arXiv.
24. Koutini, K., Eghbal-zadeh, H., and Widmer, G. (2019). Receptivefield-regularized CNN variants for acoustic scene classification. arXiv.10.33682/cjd9-kc43 ↗