ASDKit: A Toolkit for Comprehensive Evaluation of Anomalous Sound Detection Methods
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_ | 1866913940007550976 |
|---|---|
| author | Fujimura, Takuya Wilkinghoff, Kevin Imoto, Keisuke Toda, Tomoki |
| author_facet | Fujimura, Takuya Wilkinghoff, Kevin Imoto, Keisuke Toda, Tomoki |
| contents | In this paper, we introduce ASDKit, a toolkit for anomalous sound detection (ASD) task. Our aim is to facilitate ASD research by providing an open-source framework that collects and carefully evaluates various ASD methods. First, ASDKit provides training and evaluation scripts for a wide range of ASD methods, all handled within a unified framework. For instance, it includes the autoencoder-based official DCASE baseline, representative discriminative methods, and self-supervised learning-based methods. Second, it supports comprehensive evaluation on the DCASE 2020--2024 datasets, enabling careful assessment of ASD performance, which is highly sensitive to factors such as datasets and random seeds. In our experiments, we re-evaluate various ASD methods using ASDKit and identify consistently effective techniques across multiple datasets and trials. We also demonstrate that ASDKit reproduces the state-of-the-art-level performance on the considered datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10264 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ASDKit: A Toolkit for Comprehensive Evaluation of Anomalous Sound Detection Methods Fujimura, Takuya Wilkinghoff, Kevin Imoto, Keisuke Toda, Tomoki Audio and Speech Processing In this paper, we introduce ASDKit, a toolkit for anomalous sound detection (ASD) task. Our aim is to facilitate ASD research by providing an open-source framework that collects and carefully evaluates various ASD methods. First, ASDKit provides training and evaluation scripts for a wide range of ASD methods, all handled within a unified framework. For instance, it includes the autoencoder-based official DCASE baseline, representative discriminative methods, and self-supervised learning-based methods. Second, it supports comprehensive evaluation on the DCASE 2020--2024 datasets, enabling careful assessment of ASD performance, which is highly sensitive to factors such as datasets and random seeds. In our experiments, we re-evaluate various ASD methods using ASDKit and identify consistently effective techniques across multiple datasets and trials. We also demonstrate that ASDKit reproduces the state-of-the-art-level performance on the considered datasets. |
| title | ASDKit: A Toolkit for Comprehensive Evaluation of Anomalous Sound Detection Methods |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2507.10264 |