Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2509.13853 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911160459067392 |
|---|---|
| author | Huang, Shun Fang, Zhihua He, Liang |
| author_facet | Huang, Shun Fang, Zhihua He, Liang |
| contents | Unsupervised anomalous sound detection aims to detect unknown anomalous sounds by training a model using only normal audio data. Despite advancements in self-supervised methods, the issue of frequent false alarms when handling samples of the same type from different machines remains unresolved. This paper introduces a novel training technique called one-stage supervised contrastive learning (OS-SCL), which significantly addresses this problem by perturbing features in the embedding space and employing a one-stage noisy supervised contrastive learning approach. On the DCASE 2020 Challenge Task 2, it achieved 94.64\% AUC, 88.42\% pAUC, and 89.24\% mAUC using only Log-Mel features. Additionally, a time-frequency feature named TFgram is proposed, which is extracted from raw audio. This feature effectively captures critical information for anomalous sound detection, ultimately achieving 95.71\% AUC, 90.23\% pAUC, and 91.23\% mAUC. The source code is available at: \underline{www.github.com/huangswt/OS-SCL}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13853 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Noise Supervised Contrastive Learning and Feature-Perturbed for Anomalous Sound Detection Huang, Shun Fang, Zhihua He, Liang Sound Computation and Language Unsupervised anomalous sound detection aims to detect unknown anomalous sounds by training a model using only normal audio data. Despite advancements in self-supervised methods, the issue of frequent false alarms when handling samples of the same type from different machines remains unresolved. This paper introduces a novel training technique called one-stage supervised contrastive learning (OS-SCL), which significantly addresses this problem by perturbing features in the embedding space and employing a one-stage noisy supervised contrastive learning approach. On the DCASE 2020 Challenge Task 2, it achieved 94.64\% AUC, 88.42\% pAUC, and 89.24\% mAUC using only Log-Mel features. Additionally, a time-frequency feature named TFgram is proposed, which is extracted from raw audio. This feature effectively captures critical information for anomalous sound detection, ultimately achieving 95.71\% AUC, 90.23\% pAUC, and 91.23\% mAUC. The source code is available at: \underline{www.github.com/huangswt/OS-SCL}. |
| title | Noise Supervised Contrastive Learning and Feature-Perturbed for Anomalous Sound Detection |
| topic | Sound Computation and Language |
| url | https://arxiv.org/abs/2509.13853 |