Improving Anomalous Sound Detection by Distance Matrix-Based Visualization of Measurement Flaws



Published Sep 4, 2023
Nobuaki Tanaka Takeru Shiraga Yusuke Itani


Although recent DNN-based methods have improved the performance of anomalous sound detection systems, it is still difficult to deploy a system in a real environment without performance degradation. This is often due to measurement flaws such as sensor variability, poor setup, or environmental noise. Since such adverse effects are difficult to model by machine learning, a practical approach to this issue is for humans to identify such flaws and correct them. To this end, we propose a method to visualize measurement flaws as a heatmap based on the distance matrix of the samples in the dataset. This method is designed to find unexpected flaws in the measurement process. Using this method, we were able to identify measurement flaws of anomalous sound detection systems in real production lines. The robustness of anomalous sound detection can be improved by correcting the flaws found by our method.  

Abstract 154 | PDF Downloads 150



anomalous sound detection, product inspection, machine health monitoring, data visualization

S. Nandi, H. A. Toliyat, and X. Li, “Condition monitoring and fault diagnosis of electrical motors—A review,” IEEE Trans. Energy Convers., vol. 20, no. 4, pp. 719– 729, 2005.

W. Zhou, T. G. Habetler, and R. G. Harley, “Bearing condition monitoring methods for electric machines: A general review, in Proc. IEEE Int. Symp. Diagnostics Electr. Mach., Power Electron. Drives, Sep. 2007, pp. 3–6.

Z. Feng, M. Liang, and F. Chu, “Recent advances in time-frequency analysis methods for machinery fault diagnosis: A review with application examples,” Mech. Syst. Signal Process., vol. 38, no. 1, pp. 165–205, 2013.

S. Riaz, H. Elahi, K. Javaid, and T. Shahzad, “Vibration feature extraction and analysis for fault diagnosis of rotating machinery—A literature survey,” Asia Pacific J. Multidiscip. Res., vol. 5, no. 1, pp. 103–110, 2017.

Y. Koizumi, S. Saito, H. Uematsu, and N. Harada, “Optimizing acoustic feature extractor for anomalous sound detection based on neyman-pearson lemma,” in Proc. EUSIPCO, 2017, pp. 698–702.

Y. Koizumi, S. Saito, H. Uematsu, Y. Kawachi, and N. Harada, “Unsupervised Detection of Anomalous Sound based on Deep Learning and the Neyman-Pearson Lemma,” IEEE/ACM Trans. on Audio Speech and Language Processing, pp.212–224, 2019.

Y. Koizumi, S. Saito, H. Uematsu, N. Harada, and K. Imoto, “ToyADMOS: A dataset of miniature-machine operating sounds for anomalous sound detection,” in Proc. WASPAA, Oct. 2019, pp. 313–317.

H. Purohit, R. Tanabe, T. Ichige, T. Endo, Y. Nikaido, K. Suefusa, and Y. Kawaguchi, “MIMII Dataset: Sound dataset for malfunctioning industrial machine investigation and inspection,” in Proc. DCASE, Oct. 2019, pp. 209–213.

K. Suefusa, T. Nishida, H. Purohit, R. Tanabe, T. Endo, Y. Kawaguchi, “Anomalous Sound Detection Based on Interpolation Deep Neural Network,” in Proc. ICASSP, May. 2020, pp. 271–275.

G. Wichern, A. Chakrabarty, Z.-Q. Wang, and J. Le Roux, “Anomalous sound detection using attentive neural processes,” in Proc. WASPAA, 2021, pp. 186–190.

N. Harada, D. Niizumi, D. Takeuchi, Y. Ohishi, M. Yasuda, and S. Saito, “ToyADMOS2: another dataset of miniature-machine operating sounds for anomalous sound detection under domain shift conditions,” arXiv preprint arXiv:2106.02369, 2021.

K. Dohi, T. Nishida, H. Purohit, R. Tanabe, T. Endo, M. Yamamoto, Y. Nikaido, and Y. Kawaguchi, “Mimii dg: Sound dataset for malfunctioning industrial machine investigation and inspection for domain generalization task,” arXiv preprint arXiv:2205.13879, 2022.

S. Venkatesh, G. Wichern, A. Subramanian, and J. Le Roux, “Disentangled surrogate task learning for improved domain generalization in unsupervised anomalous sound detection,” DCASE2022 Challenge, Tech. Rep., 2022.

J. Luo et al., “A comparison of batch effect removal methods for enhancement of prediction performance using MAQC-II microarray gene expression data,” Pharmacogenomics J. (2010) 10, pp. 278–291.

C. Lazar et al., “Batch efect removal methods for microarray gene expression data integration: a survey,” Brief. Bioinform. vol. 14, no. 4, pp. 469–490, 2012.

D. J. McCarthy, K. R. Campbell, A. T. K. Lun, and Q. F. Wills, “Scater: pre-processing, quality control, normalization and visualization of single-cell RNA-seq data in R,” Bioinformatics, 33(8), 2017, pp. 1179–1186.

L. H. Nguyen and S. Holmes, “Ten quick tips for effective dimensionality reduction,” PLoS Comput. Biol. 15(6): e1006907, 2019.

J. T. Leek and J. D. Storey, “Capturing heterogeneity in gene expression studies by surrogate variable analysis,” PLoS Genet. 3(9): e161, 2007.

J. T. Leek, W. E. Johnson, H. S. Parker, A. E. Jaffe, and J. D. Storey, “The sva package for removing batch effects and other unwanted variation in high-throughput experiments,” Bioinformatics vol. 28, no. 6, 2012, pp. 882–883.

S. E. Reese et al., “A new statistic for identifying batch effects in high-throughput genomic data that uses guided principal component analysis,” Bioinformatics vol. 29, no. 22, 2013, pp. 2877–2883.

J. M. Franks, G. Cai, and M. L. Whitfield, “Feature specific quantile normalization enables cross-platform classification of molecular subtypes using gene expression data,” Bioinformatics, vol. 34, no. 11, 2018, pp. 1868– 1874.

C. H. You, K. A. Lee, and H. Li, “An SVM kernel with GMM-supervector based on the Bhattacharyya distance for speaker recognition,” IEEE Signal Process. Lett. vol. 16, no. 1, pp. 49–52, 2009.

N. T. Vu et al., “A first speech recognition system for Mandarin-English code-switch conversational speech,” in Proc. ICASSP, Mar. 2012, pp. 4889–4892.
Regular Session Papers