{"id":"https://openalex.org/W4408355065","doi":"https://doi.org/10.1109/icassp49660.2025.10890695","title":"Diffusion Augmentation Sub-center Modeling for Unsupervised Anomalous Sound Detection with Partially Attribute-Unavailable Conditions","display_name":"Diffusion Augmentation Sub-center Modeling for Unsupervised Anomalous Sound Detection with Partially Attribute-Unavailable Conditions","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355065","doi":"https://doi.org/10.1109/icassp49660.2025.10890695"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890695","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":"article","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/A5102661064","display_name":"Jiawei Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiawei Yin","raw_affiliation_strings":["Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702"],"affiliations":[{"raw_affiliation_string":"Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020803502","display_name":"Yu Gao","orcid":"https://orcid.org/0000-0002-2135-7872"},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Gao","raw_affiliation_strings":["Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702"],"affiliations":[{"raw_affiliation_string":"Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100710810","display_name":"Wenbin Zhang","orcid":"https://orcid.org/0000-0002-7681-7530"},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbin Zhang","raw_affiliation_strings":["Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702"],"affiliations":[{"raw_affiliation_string":"Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399640","display_name":"Tianyi Wang","orcid":"https://orcid.org/0000-0002-9419-5800"},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Wang","raw_affiliation_strings":["Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702"],"affiliations":[{"raw_affiliation_string":"Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5116479882","display_name":"Mingjun Zhang","orcid":"https://orcid.org/0000-0002-8090-5963"},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjun Zhang","raw_affiliation_strings":["Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702"],"affiliations":[{"raw_affiliation_string":"Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702","institution_ids":["https://openalex.org/I4210093653"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102661064"],"corresponding_institution_ids":["https://openalex.org/I4210093653"],"apc_list":null,"apc_paid":null,"fwci":4.7229,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93997369,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"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/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9764000177383423,"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/diffusion","display_name":"Diffusion","score":0.708721935749054},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6665739417076111},{"id":"https://openalex.org/keywords/center","display_name":"Center (category theory)","score":0.5709044933319092},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5122184157371521},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3568604588508606},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34210801124572754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32196030020713806},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2816851735115051},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06759065389633179}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.708721935749054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6665739417076111},{"id":"https://openalex.org/C2779463800","wikidata":"https://www.wikidata.org/wiki/Q5062222","display_name":"Center (category theory)","level":2,"score":0.5709044933319092},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5122184157371521},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3568604588508606},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34210801124572754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32196030020713806},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2816851735115051},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06759065389633179},{"id":"https://openalex.org/C8010536","wikidata":"https://www.wikidata.org/wiki/Q160398","display_name":"Crystallography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890695","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2136132422","https://openalex.org/W2936774411","https://openalex.org/W2963814162","https://openalex.org/W2969985801","https://openalex.org/W3015356122","https://openalex.org/W3016131548","https://openalex.org/W3035070480","https://openalex.org/W3196912073","https://openalex.org/W4309765030","https://openalex.org/W4372185032","https://openalex.org/W4372260076","https://openalex.org/W4372260191","https://openalex.org/W4372263161","https://openalex.org/W4372349138","https://openalex.org/W4381244712","https://openalex.org/W4385377018","https://openalex.org/W4392902665","https://openalex.org/W4392903511","https://openalex.org/W4392903605","https://openalex.org/W4392903798","https://openalex.org/W4392903829","https://openalex.org/W4392903901","https://openalex.org/W4392904764","https://openalex.org/W4392930794","https://openalex.org/W4402263288","https://openalex.org/W6779823529","https://openalex.org/W6788990321","https://openalex.org/W6790598508","https://openalex.org/W6848208918","https://openalex.org/W6864909175","https://openalex.org/W6869072782"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W2188431416","https://openalex.org/W3020957235","https://openalex.org/W2065091555","https://openalex.org/W2056769785","https://openalex.org/W2371189778","https://openalex.org/W1573667629"],"abstract_inverted_index":{"Current":[0],"state-of-the-art":[1],"unsupervised":[2],"anomalous":[3],"sound":[4],"detection":[5],"(ASD)":[6],"methods":[7],"typically":[8],"rely":[9],"on":[10,128],"manually":[11],"annotated":[12],"attribute":[13,38],"information":[14,39],"as":[15],"labels,":[16],"employing":[17],"auxiliary":[18],"classification":[19],"tasks":[20],"to":[21,50,113],"learn":[22,51],"an":[23],"embedding":[24,91],"space":[25],"for":[26,43,90],"normal":[27],"sounds,":[28],"which":[29],"helps":[30],"detect":[31],"anomalies":[32],"deviating":[33],"from":[34],"this":[35],"space.":[36],"However,":[37],"is":[40],"often":[41],"unavailable":[42],"certain":[44],"machine":[45,61],"types,":[46],"making":[47],"it":[48],"difficult":[49],"the":[52,59,68,129,138],"complex":[53],"intra-class":[54,115,119],"data":[55],"distribution":[56],"features":[57],"of":[58,98],"same":[60],"type.":[62],"Additionally,":[63],"limited":[64],"sample":[65],"diversity":[66,116],"in":[67,122],"target":[69],"domain":[70],"further":[71],"hinders":[72],"learning":[73],"robust":[74],"discriminative":[75,105],"features.":[76],"To":[77],"address":[78],"these":[79],"challenges,":[80],"we":[81],"propose":[82],"a":[83,109],"diffusion":[84,102],"augmentation":[85],"sub-center":[86,99],"modeling":[87],"(DASM)":[88],"approach":[89,112],"learning.":[92],"This":[93],"method":[94,140],"employs":[95],"iterative":[96],"training":[97],"modeling,":[100],"adaptive":[101],"augmentation,":[103],"and":[104,117],"feature":[106],"learning,":[107],"utilizing":[108],"min-max":[110],"optimization":[111],"maximize":[114],"minimize":[118],"distance,":[120],"resulting":[121],"more":[123],"expressive":[124],"embeddings.":[125],"Experimental":[126],"results":[127],"DCASE":[130],"2024":[131],"Challenge":[132],"Task":[133],"2":[134],"dataset":[135],"demonstrate":[136],"that":[137],"proposed":[139],"significantly":[141],"improves":[142],"ASD":[143],"performance.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}