Discriminative Neighborhood Smoothing for Generative Anomalous Sound Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913269581611008 |
|---|---|
| author | Fujimura, Takuya Imoto, Keisuke Toda, Tomoki |
| author_facet | Fujimura, Takuya Imoto, Keisuke Toda, Tomoki |
| contents | We propose discriminative neighborhood smoothing of generative anomaly scores for anomalous sound detection. While the discriminative approach is known to achieve better performance than generative approaches often, we have found that it sometimes causes significant performance degradation due to the discrepancy between the training and test data, making it less robust than the generative approach. Our proposed method aims to compensate for the disadvantages of generative and discriminative approaches by combining them. Generative anomaly scores are smoothed using multiple samples with similar discriminative features to improve the performance of the generative approach in an ensemble manner while keeping its robustness. Experimental results show that our proposed method greatly improves the original generative method, including absolute improvement of 22% in AUC and robustly works, while a discriminative method suffers from the discrepancy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_11508 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Discriminative Neighborhood Smoothing for Generative Anomalous Sound Detection Fujimura, Takuya Imoto, Keisuke Toda, Tomoki Audio and Speech Processing We propose discriminative neighborhood smoothing of generative anomaly scores for anomalous sound detection. While the discriminative approach is known to achieve better performance than generative approaches often, we have found that it sometimes causes significant performance degradation due to the discrepancy between the training and test data, making it less robust than the generative approach. Our proposed method aims to compensate for the disadvantages of generative and discriminative approaches by combining them. Generative anomaly scores are smoothed using multiple samples with similar discriminative features to improve the performance of the generative approach in an ensemble manner while keeping its robustness. Experimental results show that our proposed method greatly improves the original generative method, including absolute improvement of 22% in AUC and robustly works, while a discriminative method suffers from the discrepancy. |
| title | Discriminative Neighborhood Smoothing for Generative Anomalous Sound Detection |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2403.11508 |