{"id":"https://openalex.org/W4408352306","doi":"https://doi.org/10.1109/icassp49660.2025.10888266","title":"Disentangling Hierarchical Features for Anomalous Sound Detection Under Domain Shift","display_name":"Disentangling Hierarchical Features for Anomalous Sound Detection Under Domain Shift","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352306","doi":"https://doi.org/10.1109/icassp49660.2025.10888266"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059231561","display_name":"Jian Guan","orcid":"https://orcid.org/0000-0002-0945-1081"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Guan","raw_affiliation_strings":["Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,Harbin,China,150001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,Harbin,China,150001","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101255430","display_name":"Jiantong Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiantong Tian","raw_affiliation_strings":["Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,Harbin,China,150001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,Harbin,China,150001","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104012520","display_name":"Qiaoxi Zhu","orcid":"https://orcid.org/0000-0003-3942-0945"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiaoxi Zhu","raw_affiliation_strings":["University of Technology Sydney,Acoustics Lab,Ultimo,NSW,Australia,2007"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney,Acoustics Lab,Ultimo,NSW,Australia,2007","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062281933","display_name":"Feiyang Xiao","orcid":"https://orcid.org/0000-0001-9359-4554"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyang Xiao","raw_affiliation_strings":["Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,Harbin,China,150001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,Harbin,China,150001","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112980292","display_name":"Hejing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hejing Zhang","raw_affiliation_strings":["Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,Harbin,China,150001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,Harbin,China,150001","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080214850","display_name":"Xubo Liu","orcid":"https://orcid.org/0000-0002-2558-0959"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["University of Surrey,Centre for Vision Speech and Signal Processing,Guildford,UK,GU2 7XH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision Speech and Signal Processing,Guildford,UK,GU2 7XH","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9776999950408936,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6354537606239319},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47376421093940735},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4635547697544098},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3426237404346466},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15817204117774963},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1251775026321411},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11186963319778442}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6354537606239319},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47376421093940735},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4635547697544098},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3426237404346466},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15817204117774963},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1251775026321411},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11186963319778442},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W153185079","https://openalex.org/W2346746376","https://openalex.org/W2795889831","https://openalex.org/W2963351448","https://openalex.org/W2969893028","https://openalex.org/W2981720610","https://openalex.org/W4221140395","https://openalex.org/W4293363567","https://openalex.org/W4372185032","https://openalex.org/W4372260076","https://openalex.org/W4392903798","https://openalex.org/W4392910299","https://openalex.org/W6637618735","https://openalex.org/W6779961064","https://openalex.org/W6850002427","https://openalex.org/W6862130285","https://openalex.org/W7018478225"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2909726438"],"abstract_inverted_index":{"Anomalous":[0],"sound":[1,130],"detection":[2,37],"(ASD)":[3],"encounters":[4],"difficulties":[5],"with":[6],"domain":[7,33,152],"shift,":[8],"where":[9],"the":[10,43,52,85,106,114,135,144],"sounds":[11],"of":[12,45,116],"machines":[13],"in":[14,21,100],"target":[15],"domains":[16,23],"differ":[17],"significantly":[18,147],"from":[19,67,96],"those":[20],"source":[22],"due":[24],"to":[25,35,55,64,83,92,112],"varying":[26],"operating":[27],"conditions.":[28],"Existing":[29],"methods":[30],"typically":[31],"employ":[32],"classifiers":[34],"enhance":[36],"performance,":[38],"but":[39],"they":[40],"often":[41],"overlook":[42],"influence":[44],"domain-unrelated":[46,97],"information.":[47],"This":[48],"oversight":[49],"can":[50],"hinder":[51],"model\u2019s":[53],"ability":[54],"clearly":[56],"distinguish":[57],"between":[58],"domains,":[59],"thereby":[60],"weakening":[61],"its":[62],"capacity":[63],"differentiate":[65],"normal":[66],"abnormal":[68],"sounds.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"propose":[74],"a":[75,109],"Gradient":[76],"Reversal-based":[77],"Hierarchical":[78],"feature":[79,103],"Disentanglement":[80],"(GRHD)":[81],"method":[82,107,146],"address":[84],"above":[86],"challenge.":[87],"GRHD":[88],"uses":[89],"gradient":[90],"reversal":[91],"separate":[93],"domain-related":[94],"features":[95,119],"ones,":[98],"resulting":[99],"more":[101],"robust":[102],"representations.":[104],"Additionally,":[105],"employs":[108],"hierarchical":[110],"structure":[111],"guide":[113],"learning":[115],"fine-grained,":[117],"domain-specific":[118],"by":[120],"leveraging":[121],"available":[122],"metadata,":[123],"such":[124],"as":[125],"section":[126],"IDs":[127],"and":[128],"machine":[129],"attributes.":[131],"Experimental":[132],"results":[133],"on":[134],"DCASE":[136],"2022":[137],"Challenge":[138],"Task":[139],"2":[140],"dataset":[141],"demonstrate":[142],"that":[143],"proposed":[145],"improves":[148],"ASD":[149],"performance":[150],"under":[151],"shift.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}