Improving Anomalous Sound Detection with Attribute-aware Representation from Domain-adaptive Pre-training

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fang, Xin, Zhong, Guirui, Wang, Qing, Chu, Fan, Wang, Lei, Qian, Mengui, Cai, Mingqi, Wu, Jiangzhao, Gao, Jianqing, Du, Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908546338127872
author Fang, Xin
Zhong, Guirui
Wang, Qing
Chu, Fan
Wang, Lei
Qian, Mengui
Cai, Mingqi
Wu, Jiangzhao
Gao, Jianqing
Du, Jun
author_facet Fang, Xin
Zhong, Guirui
Wang, Qing
Chu, Fan
Wang, Lei
Qian, Mengui
Cai, Mingqi
Wu, Jiangzhao
Gao, Jianqing
Du, Jun
contents Anomalous Sound Detection (ASD) is often formulated as a machine attribute classification task, a strategy necessitated by the common scenario where only normal data is available for training. However, the exhaustive collection of machine attribute labels is laborious and impractical. To address the challenge of missing attribute labels, this paper proposes an agglomerative hierarchical clustering method for the assignment of pseudo-attribute labels using representations derived from a domain-adaptive pre-trained model, which are expected to capture machine attribute characteristics. We then apply model adaptation to this pre-trained model through supervised fine-tuning for machine attribute classification, resulting in a new state-of-the-art performance. Evaluation on the Detection and Classification of Acoustic Scenes and Events (DCASE) 2025 Challenge dataset demonstrates that our proposed approach yields significant performance gains, ultimately outperforming our previous top-ranking system in the challenge.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12845
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Anomalous Sound Detection with Attribute-aware Representation from Domain-adaptive Pre-training
Fang, Xin
Zhong, Guirui
Wang, Qing
Chu, Fan
Wang, Lei
Qian, Mengui
Cai, Mingqi
Wu, Jiangzhao
Gao, Jianqing
Du, Jun
Sound
Artificial Intelligence
Anomalous Sound Detection (ASD) is often formulated as a machine attribute classification task, a strategy necessitated by the common scenario where only normal data is available for training. However, the exhaustive collection of machine attribute labels is laborious and impractical. To address the challenge of missing attribute labels, this paper proposes an agglomerative hierarchical clustering method for the assignment of pseudo-attribute labels using representations derived from a domain-adaptive pre-trained model, which are expected to capture machine attribute characteristics. We then apply model adaptation to this pre-trained model through supervised fine-tuning for machine attribute classification, resulting in a new state-of-the-art performance. Evaluation on the Detection and Classification of Acoustic Scenes and Events (DCASE) 2025 Challenge dataset demonstrates that our proposed approach yields significant performance gains, ultimately outperforming our previous top-ranking system in the challenge.
title Improving Anomalous Sound Detection with Attribute-aware Representation from Domain-adaptive Pre-training
topic Sound
Artificial Intelligence
url https://arxiv.org/abs/2509.12845