Distributed collaborative anomalous sound detection by embedding sharing (2403.16610v1)
Abstract: To develop a machine sound monitoring system, a method for detecting anomalous sound is proposed. In this paper, we explore a method for multiple clients to collaboratively learn an anomalous sound detection model while keeping their raw data private from each other. In the context of industrial machine anomalous sound detection, each client possesses data from different machines or different operational states, making it challenging to learn through federated learning or split learning. In our proposed method, each client calculates embeddings using a common pre-trained model developed for sound data classification, and these calculated embeddings are aggregated on the server to perform anomalous sound detection through outlier exposure. Experiments showed that our proposed method improves the AUC of anomalous sound detection by an average of 6.8%.
- “Optimizing acoustic feature extractor for anomalous sound detection based on neyman-pearson lemma,” in EUSIPCO, 2017, pp. 698–702.
- “Anomalous sound detection based on interpolation deep neural network,” in ICASSP, 2020, pp. 271–275.
- “Anomalous sound event detection: A survey of machine learning based methods and applications,” Multimedia Tools and Applications, vol. 81, pp. 5537–5586, 2022.
- “Unsupervised anomalous sound detection using self-supervised classification and group masked autoencoder for density estimation,” Tech. Rep., DCASE2020 Challenge, 2020.
- “Federated learning with non-iid data,” arXiv preprint arXiv:1806.00582, 2018.
- “Communication-efficient learning of deep networks from decentralized data,” arXiv preprint arXiv:1602.05629, 2016.
- “Split learning for health: Distributed deep learning without sharing raw patient data,” in NeurIPS, 2018.
- “Auto-encoding variational bayes,” in ICLR, 2014.
- E. Tabak and C. Turner, “A family of nonparametric density estimation algorithms,” Communications on Pure and Applied Mathematics, vol. 66, pp. 145–164, 2013.
- D. P. Kingma and P. Dhariwal, “Glow: Generative flow with invertible 1x1 convolutions,” in NeurIPS, 2018.
- “Spidernet: Attention network for one-shot anomaly detection in sounds,” in ICASSP, 2020, pp. 281–285.
- “End-to-end evaluation of federated learning and split learning for internet of things,” in Proceedings of the 39th International Symposium on Reliable Distributed Systems (SRDS), 2020.
- “Learning privacy-preserving embeddings for image data to be published,” ACM Transactions on Intelligent Systems and Technology, vol. 14, no. 6, pp. 1–26, 2021.
- “Information leakage in embedding models,” in Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security. 2020, ACM.
- “Description and discussion on DCASE2020 Challenge task2: Unsupervised anomalous sound detection for machine condition monitoring,” in DCASE Workshop, 2020.
- Google AI team, “Yamnet,” Available at: https://github.com/tensorflow/models/tree/master/research/audioset/yamnet, 2020.
- “Audio set: An ontology and human-labeled dataset for audio events,” in ICASSP. IEEE, 2017, pp. 776–780.
- “Panns: Large-scale pretrained audio neural networks for audio pattern recognition,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 28, 2020.
- “Look, listen and learn more: Design choices for deep audio embeddings,” in ICASSP, 2019, pp. 3852–3856.
- “Look, listen and learn,” in IEEE International Conference on Computer Vision (ICCV), 2017.
- “Mobilefacenets: Efficient cnns for accurate real-time face verification on mobile devices,” arXiv preprint arXiv:1804.07573, 2018.
- “Anomalous sound detection using cnn-based features by self supervised learning,” Tech. Rep., DCASE2021 Challenge, 2021.
- “Arcface: Additive angular margin loss for deep face recognition,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4690–4699.
- “Decoupled weight decay regularization,” in ICLR, 2019.
- “Flow-based self-supervised density estimation for anomalous sound detection,” in ICASSP, 2021.