Software & Data Downloads — anomaly-score-normalization

Local Density-Based Anomaly Score Normalization for Domain Generalization for local density-based anomaly score normalization for domain generalization applied to unsupervised anomalous sound detection using the DCASE 2020, 2023, and 2024 task 2 datasets.

PyTorch code for local density-based anomaly score normalization for domain generalization applied to unsupervised anomalous sound detection using the DCASE 2020, 2023, and 2024 task 2 datasets.

    •  Wilkinghoff, K., Yang, H., Ebbers, J., Germain, F.G., Wichern, G., Le Roux, J., "Keeping the Balance: Anomaly Score Calculation for Domain Generalization", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49660.2025.10888402, April 2025.
      BibTeX TR2025-030 PDF Software
      • @inproceedings{Wilkinghoff2025mar,
      • author = {{{Wilkinghoff, Kevin and Yang, Haici and Ebbers, Janek and Germain, François G and Wichern, Gordon and Le Roux, Jonathan}}},
      • title = {{{Keeping the Balance: Anomaly Score Calculation for Domain Generalization}}},
      • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
      • year = 2025,
      • month = apr,
      • doi = {10.1109/ICASSP49660.2025.10888402},
      • url = {https://www.merl.com/publications/TR2025-030}
      • }
    •  Wilkinghoff, K., Yang, H., Ebbers, J., Germain, F.G., Wichern, G., Le Roux, J., "Local Density-Based Anomaly Score Normalization for Domain Generalization", IEEE Transactions on Audio, Speech and Language Processing, January 2026.
      BibTeX TR2026-010 PDF Software
      • @article{Wilkinghoff2026jan,
      • author = {Wilkinghoff, Kevin and Yang, Haici and Ebbers, Janek and Germain, François G and Wichern, Gordon and {Le Roux}, Jonathan},
      • title = {{Local Density-Based Anomaly Score Normalization for Domain Generalization}},
      • journal = {IEEE Transactions on Audio, Speech and Language Processing},
      • year = 2026,
      • month = jan,
      • url = {https://www.merl.com/publications/TR2026-010}
      • }

    Access software at https://github.com/merlresearch/anomaly-score-normalization.