First-Shot Unsupervised Anomalous Sound Detection With Unknown Anomalies Estimated by Metadata-Assisted Audio Generation (2310.14173v2)
Abstract: First-shot (FS) unsupervised anomalous sound detection (ASD) is a brand-new task introduced in DCASE 2023 Challenge Task 2, where the anomalous sounds for the target machine types are unseen in training. Existing methods often rely on the availability of normal and abnormal sound data from the target machines. However, due to the lack of anomalous sound data for the target machine types, it becomes challenging when adapting the existing ASD methods to the first-shot task. In this paper, we propose a new framework for the first-shot unsupervised ASD, where metadata-assisted audio generation is used to estimate unknown anomalies, by utilising the available machine information (i.e., metadata and sound data) to fine-tune a text-to-audio generation model for generating the anomalous sounds that contain unique acoustic characteristics accounting for each different machine type. We then use the method of Time-Weighted Frequency domain audio Representation with Gaussian Mixture Model (TWFR-GMM) as the backbone to achieve the first-shot unsupervised ASD. Our proposed FS-TWFR-GMM method achieves competitive performance amongst top systems in DCASE 2023 Challenge Task 2, while requiring only 1% model parameters for detection, as validated in our experiments.
- Y. Zeng, H. Liu, L. Xu, Y. Zhou, and L. Gan, “Robust anomaly sound detection framework for machine condition monitoring,” DCASE2022 Challenge, Tech. Rep., 2022.
- Y. Liu, J. Guan, Q. Zhu, and W. Wang, “Anomalous sound detection using spectral-temporal information fusion,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2022, pp. 816–820.
- J. Guan, Y. Liu, Q. Zhu, T. Zheng, J. Han, and W. Wang, “Time-weighted frequency domain audio representation with GMM estimator for anomalous sound detection,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2023, pp. 1–5.
- N. Harada, D. Niizumi, Y. Ohishi, D. Takeuchi, and M. Yasuda, “First-shot anomaly sound detection for machine condition monitoring: A domain generalization baseline,” arXiv preprint arXiv:2303.00455, 2023.
- H. Liu, Z. Chen, Y. Yuan, X. Mei, X. Liu, D. Mandic, W. Wang, and M. D. Plumbley, “AudioLDM: Text-to-audio generation with latent diffusion models,” in Proc. Int. Conf. Mach. Learn. (ICML), 2023.
- K. Wilkinghoff, “Fraunhofer FKIE submission for task 2: First-shot unsupervised anomalous sound detection for machine condition monitoring,” DCASE2023 Challenge, Tech. Rep., 2023.
- E. Zahedi, M. Saraee, F. S. Masoumi, and M. Yazdinejad, “Regularized contrastive masked autoencoder model for machinery anomaly detection using diffusion-based data augmentation,” Algorithms, vol. 16, no. 9, p. 431, 2023.
- T. Inoue, P. Vinayavekhin, S. Morikuni, S. Wang, T. Hoang Trong, D. Wood, M. Tatsubori, and R. Tachibana, “Detection of anomalous sounds for machine condition monitoring using classification confidence,” in Proc. DCASE Workshop, 2020, pp. 66–70.
- H. Chen, Y. Song, Z. Zhuo, Y. Zhou, Y.-H. Li, H. Xue, and I. McLoughlin, “An effective anomalous sound detection method based on representation learning with simulated anomalies,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2023, pp. 1–5.
- J. Tian, H. Zhang, Q. Zhu, F. Xiao, H. Liu, X. Mei, Y. Liu, W. Wang, and J. Guan, “First-shot anomalous sound detection with GMM clustering and finetuned attribute classification using audio pretrained model,” DCASE2023 Challenge, Tech. Rep., 2023.
- K. T. Mai, T. Davies, L. D. Griffin, and E. Benetos, “Explaining the decision of anomalous sound detectors,” in Proc. DCASE Workshop, 2022.
- B. Elizalde, S. Deshmukh, M. Al Ismail, and H. Wang, “CLAP learning audio concepts from natural language supervision,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2023, pp. 1–5.
- 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. IEEE Workshop Appl. Signal Process. Audio and Acoust. (WASPAA), 2019, pp. 313–317.
- J. Wang, J. Wang, S. Chen, Y. Sun, and M. Liu, “Anomaly sound detection system based on multi-dimensional attention module,” DCASE2023 Challenge, Tech. Rep., 2023.
- Z. Lv, B. Han, Z. Chen, Y. Qian, J. Ding, and J. Liu, “Unsupervised anomalous detection based on unsupervised pretrained models,” DCASE2023 Challenge, Tech. Rep., 2023.
- A. Jiang, Q. Hou, J. Liu, P. Fan, J. Ma, C. Lu, Y. Zhai, Y. Deng, and W.-Q. Zhang, “THUEE system for first-shot unsupervised anomalous sound detection for machine condition monitoring,” DCASE2023 Challenge, Tech. Rep., 2023.
- K. Dohi, T. Endo, H. Purohit, R. Tanabe, and Y. Kawaguchi, “Flow-based self-supervised density estimation for anomalous sound detection,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2021, pp. 336–340.
- J. Guan, F. Xiao, Y. Liu, Q. Zhu, and W. Wang, “Anomalous sound detection using audio representation with machine ID based contrastive learning pretraining,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2023, pp. 1–5.