HIERARCHICAL METADATA INFORMATION CONSTRAINED SELF-SUPERVISED LEARNING FOR ANOMALOUS SOUND DETECTION UNDER DOMAIN SHIFT

Lan, H; Zhu, Q; Guan, J; Wei, Y; Wang, W

HIERARCHICAL METADATA INFORMATION CONSTRAINED SELF-SUPERVISED LEARNING FOR ANOMALOUS SOUND DETECTION UNDER DOMAIN SHIFT

Lan, H Zhu, Q

Guan, J Wei, Y Wang, W

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Conference Proceeding
Citation:: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2024, pp. 7670-7674
Issue Date:: 2024-01-01

Recently Added

	Filename	Description	Size
	1721028.pdf	Published version	1.42 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is new to OPUS and is not currently available.

Full metadata record

Field	Value	Language
dc.contributor.author	Lan, H
dc.contributor.author	Zhu, Q https://orcid.org/0000-0003-3942-0945
dc.contributor.author	Guan, J
dc.contributor.author	Wei, Y
dc.contributor.author	Wang, W
dc.date	2024-04-14
dc.date.accessioned	2024-08-07T05:23:00Z
dc.date.available	2024-08-07T05:23:00Z
dc.date.issued	2024-01-01
dc.identifier.citation	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2024, pp. 7670-7674
dc.identifier.issn	1520-6149
dc.identifier.uri	http://hdl.handle.net/10453/180305
dc.description.abstract	Self-supervised learning methods have achieved promising performance for anomalous sound detection (ASD) under domain shift by incorporating the metadata of domain shift types and machine sound attributes in feature learning. However, the relation between domain shifts and machine sound attributes has yet to be fully utilised despite their potential benefits for characterising domain shifts. This paper presents a hierarchical metadata information constrained self-supervised ASD method, where the hierarchical relation between domain shift types (section IDs) and attributes is constructed and used as constraints to improve feature representation. In addition, we propose an attribute-group-centre based method for calculating the anomaly score under the domain shift condition. Experiments show improved audio feature learning over the state-of-the-art methods in DCASE 2022 challenge Task 2.
dc.language	en
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartof	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
dc.relation.ispartof	ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
dc.relation.isbasedon	10.1109/ICASSP48485.2024.10446044
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.title	HIERARCHICAL METADATA INFORMATION CONSTRAINED SELF-SUPERVISED LEARNING FOR ANOMALOUS SOUND DETECTION UNDER DOMAIN SHIFT
dc.type	Conference Proceeding
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	recently_added	*
dc.date.updated	2024-08-07T05:22:58Z
pubs.finish-date	2024-04-19
pubs.publication-status	Published
pubs.start-date	2024-04-14

Abstract:

Self-supervised learning methods have achieved promising performance for anomalous sound detection (ASD) under domain shift by incorporating the metadata of domain shift types and machine sound attributes in feature learning. However, the relation between domain shifts and machine sound attributes has yet to be fully utilised despite their potential benefits for characterising domain shifts. This paper presents a hierarchical metadata information constrained self-supervised ASD method, where the hierarchical relation between domain shift types (section IDs) and attributes is constructed and used as constraints to improve feature representation. In addition, we propose an attribute-group-centre based method for calculating the anomaly score under the domain shift condition. Experiments show improved audio feature learning over the state-of-the-art methods in DCASE 2022 challenge Task 2.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/180305