Improvements of Discriminative Feature Space Training for Anomalous Sound Detection in Unlabeled Conditions
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917775580069888 |
|---|---|
| author | Fujimura, Takuya Kuroyanagi, Ibuki Toda, Tomoki |
| author_facet | Fujimura, Takuya Kuroyanagi, Ibuki Toda, Tomoki |
| contents | In anomalous sound detection, the discriminative method has demonstrated superior performance. This approach constructs a discriminative feature space through the classification of the meta-information labels for normal sounds. This feature space reflects the differences in machine sounds and effectively captures anomalous sounds. However, its performance significantly degrades when the meta-information labels are missing. In this paper, we improve the performance of a discriminative method under unlabeled conditions by two approaches. First, we enhance the feature extractor to perform better under unlabeled conditions. Our enhanced feature extractor utilizes multi-resolution spectrograms with a new training strategy. Second, we propose various pseudo-labeling methods to effectively train the feature extractor. The experimental evaluations show that the proposed feature extractor and pseudo-labeling methods significantly improve performance under unlabeled conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09332 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improvements of Discriminative Feature Space Training for Anomalous Sound Detection in Unlabeled Conditions Fujimura, Takuya Kuroyanagi, Ibuki Toda, Tomoki Audio and Speech Processing Sound In anomalous sound detection, the discriminative method has demonstrated superior performance. This approach constructs a discriminative feature space through the classification of the meta-information labels for normal sounds. This feature space reflects the differences in machine sounds and effectively captures anomalous sounds. However, its performance significantly degrades when the meta-information labels are missing. In this paper, we improve the performance of a discriminative method under unlabeled conditions by two approaches. First, we enhance the feature extractor to perform better under unlabeled conditions. Our enhanced feature extractor utilizes multi-resolution spectrograms with a new training strategy. Second, we propose various pseudo-labeling methods to effectively train the feature extractor. The experimental evaluations show that the proposed feature extractor and pseudo-labeling methods significantly improve performance under unlabeled conditions. |
| title | Improvements of Discriminative Feature Space Training for Anomalous Sound Detection in Unlabeled Conditions |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2409.09332 |