Contrastive Learning with Spectrum Information Augmentation in Abnormal Sound Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909797506351104 |
|---|---|
| author | Meng, Xinxin Guo, Jiangtao Zhang, Yunxiang Huang, Shun |
| author_facet | Meng, Xinxin Guo, Jiangtao Zhang, Yunxiang Huang, Shun |
| contents | The outlier exposure method is an effective approach to address the unsupervised anomaly sound detection problem. The key focus of this method is how to make the model learn the distribution space of normal data. Based on biological perception and data analysis, it is found that anomalous audio and noise often have higher frequencies. Therefore, we propose a data augmentation method for high-frequency information in contrastive learning. This enables the model to pay more attention to the low-frequency information of the audio, which represents the normal operational mode of the machine. We evaluated the proposed method on the DCASE 2020 Task 2. The results showed that our method outperformed other contrastive learning methods used on this dataset. We also evaluated the generalizability of our method on the DCASE 2022 Task 2 dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15570 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Contrastive Learning with Spectrum Information Augmentation in Abnormal Sound Detection Meng, Xinxin Guo, Jiangtao Zhang, Yunxiang Huang, Shun Sound Artificial Intelligence Audio and Speech Processing The outlier exposure method is an effective approach to address the unsupervised anomaly sound detection problem. The key focus of this method is how to make the model learn the distribution space of normal data. Based on biological perception and data analysis, it is found that anomalous audio and noise often have higher frequencies. Therefore, we propose a data augmentation method for high-frequency information in contrastive learning. This enables the model to pay more attention to the low-frequency information of the audio, which represents the normal operational mode of the machine. We evaluated the proposed method on the DCASE 2020 Task 2. The results showed that our method outperformed other contrastive learning methods used on this dataset. We also evaluated the generalizability of our method on the DCASE 2022 Task 2 dataset. |
| title | Contrastive Learning with Spectrum Information Augmentation in Abnormal Sound Detection |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2509.15570 |