{"id":"https://openalex.org/W4406859059","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849062","title":"Annotation-free Fine-tuning for Unsupervised Anomalous Sound Detection","display_name":"Annotation-free Fine-tuning for Unsupervised Anomalous Sound Detection","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406859059","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849062"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5074020930","display_name":"Kai Guo","orcid":"https://orcid.org/0000-0001-7140-8693"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Guo","raw_affiliation_strings":["Beijing Institute of Technology,School of Information and Electronics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Information and Electronics,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100642395","display_name":"Xiang Xie","orcid":"https://orcid.org/0000-0002-5135-0110"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Xie","raw_affiliation_strings":["Beijing Institute of Technology,School of Information and Electronics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Information and Electronics,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027555657","display_name":"Fengrun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengrun Zhang","raw_affiliation_strings":["Beijing Institute of Technology,School of Information and Electronics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Information and Electronics,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33081169,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9973999857902527,"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":0.9973999857902527,"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/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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":0.9876000285148621,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7107904553413391},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6564051508903503},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5432161092758179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4506448209285736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32714641094207764},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1538224220275879},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06624472141265869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7107904553413391},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6564051508903503},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5432161092758179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4506448209285736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32714641094207764},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1538224220275879},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06624472141265869}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":17,"referenced_works":["https://openalex.org/W2129281431","https://openalex.org/W2167917621","https://openalex.org/W2593116425","https://openalex.org/W3015356122","https://openalex.org/W3209059054","https://openalex.org/W4221140395","https://openalex.org/W4372185032","https://openalex.org/W4372260191","https://openalex.org/W4388117975","https://openalex.org/W4392902665","https://openalex.org/W4392904001","https://openalex.org/W6631190155","https://openalex.org/W6682141768","https://openalex.org/W6750068885","https://openalex.org/W6784066080","https://openalex.org/W6852385146","https://openalex.org/W6869072782"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328"],"abstract_inverted_index":{"The":[0,78],"goal":[1],"of":[2,44,118],"unsupervised":[3,58,87,108],"anomalous":[4,14,59,88,109,115],"sound":[5,60,89,110],"detection":[6,61,116],"(ASD)":[7],"for":[8,20,86],"industrial":[9,51],"machines":[10],"is":[11,25,81],"to":[12,26,33],"identify":[13],"sounds":[15,19],"using":[16,68],"only":[17],"normal":[18],"training.":[21],"A":[22],"common":[23],"method":[24,62,80,99,131],"use":[27],"attribute":[28,47,69,141],"information":[29,48],"as":[30],"auxiliary":[31,46],"labels":[32],"train":[34],"ASD":[35,135],"models.":[36],"However,":[37],"this":[38],"approach":[39],"often":[40],"faces":[41],"the":[42,102,114],"challenge":[43],"obtaining":[45],"in":[49],"complex":[50],"environments.":[52],"This":[53],"paper":[54],"proposes":[55],"a":[56,74],"novel":[57],"that":[63,100,129,137],"fine-tunes":[64],"pre-trained":[65],"models":[66],"without":[67],"information,":[70],"achieved":[71],"by":[72],"training":[73],"machine":[75,103],"type":[76,104],"classifier.":[77],"proposed":[79],"called":[82],"Annotation-Free":[83],"Fine-tuning":[84],"(AFF)":[85],"detection.":[90],"In":[91],"addition,":[92],"we":[93],"propose":[94],"an":[95,107],"anomaly":[96],"score":[97],"calculation":[98],"combines":[101],"classifier":[105],"with":[106],"estimator,":[111],"further":[112],"improving":[113],"performance":[117],"AFF.":[119],"Experiments":[120],"on":[121],"DCASE":[122],"2024":[123],"Task":[124],"2":[125],"development":[126],"dataset":[127],"indicate":[128],"our":[130],"outperforms":[132],"other":[133],"typical":[134],"methods":[136],"do":[138],"not":[139],"utilize":[140],"information.":[142]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}