{"id":"https://openalex.org/W4408351836","doi":"https://doi.org/10.1109/icassp49660.2025.10890020","title":"Improvements of Discriminative Feature Space Training for Anomalous Sound Detection in Unlabeled Conditions","display_name":"Improvements of Discriminative Feature Space Training for Anomalous Sound Detection in Unlabeled Conditions","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408351836","doi":"https://doi.org/10.1109/icassp49660.2025.10890020"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890020","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/A5048172594","display_name":"Takuya Fujimura","orcid":"https://orcid.org/0000-0003-1726-8372"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takuya Fujimura","raw_affiliation_strings":["Nagoya University,Graduate School of Informatics,Nagoya,Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Graduate School of Informatics,Nagoya,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074471104","display_name":"Ibuki Kuroyanagi","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ibuki Kuroyanagi","raw_affiliation_strings":["Nagoya University,Graduate School of Informatics,Nagoya,Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Graduate School of Informatics,Nagoya,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006808971","display_name":"Tomoki Toda","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Information Technology Center,Nagoya,Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Information Technology Center,Nagoya,Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048172594"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":6.5456,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95777632,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9782000184059143,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9782000184059143,"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/T11309","display_name":"Music and Audio Processing","score":0.9312999844551086,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9232000112533569,"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/discriminative-model","display_name":"Discriminative model","score":0.8452667593955994},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.64506596326828},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5728175044059753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5520593523979187},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5409392714500427},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5329262614250183},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5251883268356323},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5136739611625671},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4877098500728607},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44339823722839355},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19754526019096375},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08329129219055176}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8452667593955994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.64506596326828},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5728175044059753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5520593523979187},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5409392714500427},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5329262614250183},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5251883268356323},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5136739611625671},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4877098500728607},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44339823722839355},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19754526019096375},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08329129219055176},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890020","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2096733369","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2889326414","https://openalex.org/W2939574508","https://openalex.org/W2963814162","https://openalex.org/W2969985801","https://openalex.org/W3015356122","https://openalex.org/W3094550259","https://openalex.org/W3162150435","https://openalex.org/W3201549834","https://openalex.org/W4221140395","https://openalex.org/W4312657626","https://openalex.org/W4312749585","https://openalex.org/W4372185032","https://openalex.org/W4372263161","https://openalex.org/W4388117217","https://openalex.org/W4389076443","https://openalex.org/W4392902665","https://openalex.org/W4392903829","https://openalex.org/W4404577515","https://openalex.org/W6751494907","https://openalex.org/W6757817989","https://openalex.org/W6779961064","https://openalex.org/W6850002427","https://openalex.org/W6852385146","https://openalex.org/W6864909175","https://openalex.org/W6869072782"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W156213964","https://openalex.org/W2050960118"],"abstract_inverted_index":{"In":[0,53],"anomalous":[1,40],"sound":[2],"detection,":[3],"the":[4,19,22,32,48,58,73,103,111],"discriminative":[5,15,62],"method":[6,63],"has":[7],"demonstrated":[8],"superior":[9],"performance.":[10],"This":[11,28],"approach":[12],"constructs":[13],"a":[14,61,90],"feature":[16,29,74,84,104,113],"space":[17,30],"through":[18],"classification":[20],"of":[21,60],"meta-information":[23,49],"labels":[24,50],"for":[25],"normal":[26],"sounds.":[27,41],"reflects":[31],"differences":[33],"in":[34],"machine":[35],"sounds":[36],"and":[37,115],"effectively":[38,101],"captures":[39],"However,":[42],"its":[43],"performance":[44,59,120],"significantly":[45,118],"degrades":[46],"when":[47],"are":[51],"missing.":[52],"this":[54],"paper,":[55],"we":[56,71,95],"improve":[57,119],"under":[64,79,121],"unlabeled":[65,80,122],"conditions":[66],"by":[67],"two":[68],"approaches.":[69],"First,":[70],"enhance":[72],"extractor":[75,85,114],"to":[76,100],"perform":[77],"better":[78],"conditions.":[81,123],"Our":[82],"enhanced":[83],"utilizes":[86],"multi-resolution":[87],"spectrograms":[88],"with":[89],"new":[91],"training":[92],"strategy.":[93],"Second,":[94],"propose":[96],"various":[97],"pseudo-labeling":[98,116],"methods":[99,117],"train":[102],"extractor.":[105],"The":[106],"experimental":[107],"evaluations":[108],"show":[109],"that":[110],"proposed":[112]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}