Disentangling Hierarchical Features for Anomalous Sound Detection Under Domain Shift
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910771400671232 |
|---|---|
| author | Guan, Jian Tian, Jiantong Zhu, Qiaoxi Xiao, Feiyang Zhang, Hejing Liu, Xubo |
| author_facet | Guan, Jian Tian, Jiantong Zhu, Qiaoxi Xiao, Feiyang Zhang, Hejing Liu, Xubo |
| contents | Anomalous sound detection (ASD) encounters difficulties with domain shift, where the sounds of machines in target domains differ significantly from those in source domains due to varying operating conditions. Existing methods typically employ domain classifiers to enhance detection performance, but they often overlook the influence of domain-unrelated information. This oversight can hinder the model's ability to clearly distinguish between domains, thereby weakening its capacity to differentiate normal from abnormal sounds. In this paper, we propose a Gradient Reversal-based Hierarchical feature Disentanglement (GRHD) method to address the above challenge. GRHD uses gradient reversal to separate domain-related features from domain-unrelated ones, resulting in more robust feature representations. Additionally, the method employs a hierarchical structure to guide the learning of fine-grained, domain-specific features by leveraging available metadata, such as section IDs and machine sound attributes. Experimental results on the DCASE 2022 Challenge Task 2 dataset demonstrate that the proposed method significantly improves ASD performance under domain shift. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01604 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Disentangling Hierarchical Features for Anomalous Sound Detection Under Domain Shift Guan, Jian Tian, Jiantong Zhu, Qiaoxi Xiao, Feiyang Zhang, Hejing Liu, Xubo Sound Audio and Speech Processing Anomalous sound detection (ASD) encounters difficulties with domain shift, where the sounds of machines in target domains differ significantly from those in source domains due to varying operating conditions. Existing methods typically employ domain classifiers to enhance detection performance, but they often overlook the influence of domain-unrelated information. This oversight can hinder the model's ability to clearly distinguish between domains, thereby weakening its capacity to differentiate normal from abnormal sounds. In this paper, we propose a Gradient Reversal-based Hierarchical feature Disentanglement (GRHD) method to address the above challenge. GRHD uses gradient reversal to separate domain-related features from domain-unrelated ones, resulting in more robust feature representations. Additionally, the method employs a hierarchical structure to guide the learning of fine-grained, domain-specific features by leveraging available metadata, such as section IDs and machine sound attributes. Experimental results on the DCASE 2022 Challenge Task 2 dataset demonstrate that the proposed method significantly improves ASD performance under domain shift. |
| title | Disentangling Hierarchical Features for Anomalous Sound Detection Under Domain Shift |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2501.01604 |