{"id":"https://openalex.org/W4392903798","doi":"https://doi.org/10.1109/icassp48485.2024.10448451","title":"First-Shot Unsupervised Anomalous Sound Detection with Unknown Anomalies Estimated by Metadata-Assisted Audio Generation","display_name":"First-Shot Unsupervised Anomalous Sound Detection with Unknown Anomalies Estimated by Metadata-Assisted Audio Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903798","doi":"https://doi.org/10.1109/icassp48485.2024.10448451"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5112980292","display_name":"Hejing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I1308199089","display_name":"Harbin University","ror":"https://ror.org/00ey9xa07","country_code":"CN","type":"education","lineage":["https://openalex.org/I1308199089"]},{"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","Group of Intelligent Signal Processing, College of Computer Science and Technology, Harbin Engineering University, Harbin, China","National Engineering Laboratory for Modeling and Emulation in E-Government, Harbin Engineering University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I151727225","https://openalex.org/I1308199089"]},{"raw_affiliation_string":"Group of Intelligent Signal Processing, College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"National Engineering Laboratory for Modeling and Emulation in E-Government, Harbin Engineering University, Harbin, China","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,Centre for Audio, Acoustics and Vibration,Ultimo,Australia","Centre for Audio, Acoustics and Vibration, University of Technology Sydney, Ultimo, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney,Centre for Audio, Acoustics and Vibration,Ultimo,Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"Centre for Audio, Acoustics and Vibration, University of Technology Sydney, Ultimo, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059231561","display_name":"Jian Guan","orcid":"https://orcid.org/0000-0002-0945-1081"},"institutions":[{"id":"https://openalex.org/I1308199089","display_name":"Harbin University","ror":"https://ror.org/00ey9xa07","country_code":"CN","type":"education","lineage":["https://openalex.org/I1308199089"]},{"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","National Engineering Laboratory for Modeling and Emulation in E-Government, Harbin Engineering University, Harbin, China","Group of Intelligent Signal Processing, College of Computer Science and Technology, Harbin Engineering University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I151727225","https://openalex.org/I1308199089"]},{"raw_affiliation_string":"National Engineering Laboratory for Modeling and Emulation in E-Government, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"Group of Intelligent Signal Processing, College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089924305","display_name":"Haohe Liu","orcid":"https://orcid.org/0000-0003-1036-7888"},"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":"Haohe Liu","raw_affiliation_strings":["University of Surrey,Centre for Vision Speech and Signal Processing,Guildford,UK","Centre for Vision Speech and Signal Processing, University of Surrey, Guildford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision Speech and Signal Processing,Guildford,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"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/I1308199089","display_name":"Harbin University","ror":"https://ror.org/00ey9xa07","country_code":"CN","type":"education","lineage":["https://openalex.org/I1308199089"]},{"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","Group of Intelligent Signal Processing, College of Computer Science and Technology, Harbin Engineering University, Harbin, China","National Engineering Laboratory for Modeling and Emulation in E-Government, Harbin Engineering University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I151727225","https://openalex.org/I1308199089"]},{"raw_affiliation_string":"Group of Intelligent Signal Processing, College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"National Engineering Laboratory for Modeling and Emulation in E-Government, Harbin Engineering University, Harbin, China","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/I1308199089","display_name":"Harbin University","ror":"https://ror.org/00ey9xa07","country_code":"CN","type":"education","lineage":["https://openalex.org/I1308199089"]},{"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","Group of Intelligent Signal Processing, College of Computer Science and Technology, Harbin Engineering University, Harbin, China","National Engineering Laboratory for Modeling and Emulation in E-Government, Harbin Engineering University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I151727225","https://openalex.org/I1308199089"]},{"raw_affiliation_string":"Group of Intelligent Signal Processing, College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"National Engineering Laboratory for Modeling and Emulation in E-Government, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070892237","display_name":"Xinhao Mei","orcid":"https://orcid.org/0000-0001-6079-5130"},"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":"Xinhao Mei","raw_affiliation_strings":["University of Surrey,Centre for Vision Speech and Signal Processing,Guildford,UK","Centre for Vision Speech and Signal Processing, University of Surrey, Guildford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision Speech and Signal Processing,Guildford,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","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","Centre for Vision Speech and Signal Processing, University of Surrey, Guildford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision Speech and Signal Processing,Guildford,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"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":"Wenwu Wang","raw_affiliation_strings":["University of Surrey,Centre for Vision Speech and Signal Processing,Guildford,UK","Centre for Vision Speech and Signal Processing, University of Surrey, Guildford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision Speech and Signal Processing,Guildford,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1271","last_page":"1275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9922999739646912,"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":0.9897000193595886,"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/metadata","display_name":"Metadata","score":0.8479163646697998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7976735234260559},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6478378176689148},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6139289140701294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5499246120452881},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4496236741542816},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4409422278404236},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4393021762371063},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43007326126098633},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4295964539051056},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42804521322250366},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07965654134750366},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0636606514453888}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8479163646697998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976735234260559},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6478378176689148},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6139289140701294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5499246120452881},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4496236741542816},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4409422278404236},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4393021762371063},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43007326126098633},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4295964539051056},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42804521322250366},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07965654134750366},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0636606514453888},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2997122788","https://openalex.org/W3162150435","https://openalex.org/W4221140395","https://openalex.org/W4372185032","https://openalex.org/W4372260076","https://openalex.org/W4372266552","https://openalex.org/W4381244712","https://openalex.org/W4386546994","https://openalex.org/W4388117975","https://openalex.org/W6779961064","https://openalex.org/W6849109464","https://openalex.org/W6850002427","https://openalex.org/W6852385146"],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2773965352","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010"],"abstract_inverted_index":{"First-shot":[0],"(FS)":[1],"unsupervised":[2,86,154],"anomalous":[3,20,54,118],"sound":[4,42,55,107],"detection":[5],"(ASD)":[6],"is":[7,92],"a":[8,80,111],"brand-new":[9],"task":[10],"introduced":[11],"in":[12,29,166,182],"DCASE":[13,167],"2023":[14,168],"Challenge":[15,169],"Task":[16,170],"2,":[17,171],"where":[18,88],"the":[19,23,36,45,51,58,67,72,84,100,117,134,148,152],"sounds":[21,119],"for":[22,57,83,115,126,178],"target":[24,46,59],"machine":[25,60,102,129],"types":[26],"are":[27],"unseen":[28],"training.":[30],"Existing":[31],"methods":[32,70],"often":[33],"rely":[34],"on":[35],"availability":[37],"of":[38,53,136],"normal":[39],"and":[40,106],"abnormal":[41],"data":[43,56],"from":[44],"machines.":[47],"However,":[48],"due":[49],"to":[50,71,94,109,150],"lack":[52],"types,":[61],"it":[62],"becomes":[63],"challenging":[64],"when":[65],"adapting":[66],"existing":[68],"ASD":[69],"first-shot":[73,85,153],"task.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78],"propose":[79],"new":[81],"framework":[82],"ASD,":[87],"metadata-assisted":[89],"audio":[90,140],"generation":[91,113],"used":[93],"estimate":[95],"unknown":[96],"anomalies,":[97],"by":[98],"utilising":[99],"available":[101],"information":[103],"(i.e.,":[104],"metadata":[105],"data)":[108],"fine-tune":[110],"text-to-audio":[112],"model":[114,176],"generating":[116],"that":[120],"contain":[121],"unique":[122],"acoustic":[123],"characteristics":[124],"accounting":[125],"each":[127],"different":[128],"type.":[130],"We":[131],"then":[132],"use":[133],"method":[135,159],"Time-Weighted":[137],"Frequency":[138],"domain":[139],"Representation":[141],"with":[142],"Gaussian":[143],"Mixture":[144],"Model":[145],"(TWFRGMM)":[146],"as":[147,180],"backbone":[149],"achieve":[151],"ASD.":[155],"Our":[156],"proposed":[157],"FS-TWFR-GMM":[158],"achieves":[160],"competitive":[161],"performance":[162],"amongst":[163],"top":[164],"systems":[165],"while":[172],"requiring":[173],"only":[174],"1%":[175],"parameters":[177],"detection,":[179],"validated":[181],"our":[183],"experiments.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
