{"id":"https://openalex.org/W4406858729","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848563","title":"Unsupervised Anomalous Sound Detection Using Timbral and Human Voice Disorder-Related Acoustic Features","display_name":"Unsupervised Anomalous Sound Detection Using Timbral and Human Voice Disorder-Related Acoustic Features","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858729","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848563"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848563","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":"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/A5116046371","display_name":"Malik Akbar Hashemi Rafsanjani","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Malik Akbar Hashemi Rafsanjani","raw_affiliation_strings":["Bandung Institute of Technology,Bandung,Indonesia"],"affiliations":[{"raw_affiliation_string":"Bandung Institute of Technology,Bandung,Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005680805","display_name":"Candy Olivia Mawalim","orcid":"https://orcid.org/0000-0001-9853-8893"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Candy Olivia Mawalim","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,Nomi,Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Nomi,Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109119353","display_name":"Dessi Puji Lestari","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dessi Puji Lestari","raw_affiliation_strings":["Bandung Institute of Technology,Bandung,Indonesia"],"affiliations":[{"raw_affiliation_string":"Bandung Institute of Technology,Bandung,Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology,Nara,Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Nara,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014199725","display_name":"Masashi Unoki","orcid":"https://orcid.org/0000-0002-6605-2052"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Unoki","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,Nomi,Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Nomi,Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5116046371"],"corresponding_institution_ids":["https://openalex.org/I134635517"],"apc_list":null,"apc_paid":null,"fwci":0.7471,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73255876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9811999797821045,"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":0.9811999797821045,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9739000201225281,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9663000106811523,"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":0.6277974843978882},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5994292497634888},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5584610104560852},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3926585912704468},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06547898054122925}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6277974843978882},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5994292497634888},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5584610104560852},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3926585912704468},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06547898054122925}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848563","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":[{"id":"https://openalex.org/F4320338241","display_name":"Sakura Science Exchange Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1512302197","https://openalex.org/W2045884199","https://openalex.org/W2063547421","https://openalex.org/W2093911337","https://openalex.org/W2100534701","https://openalex.org/W2122646361","https://openalex.org/W2127618892","https://openalex.org/W2158143121","https://openalex.org/W2159785329","https://openalex.org/W2171630550","https://openalex.org/W2528333531","https://openalex.org/W2596043126","https://openalex.org/W2766388946","https://openalex.org/W2768329238","https://openalex.org/W2922706279","https://openalex.org/W2937233641","https://openalex.org/W2971026201","https://openalex.org/W2982294822","https://openalex.org/W2996395154","https://openalex.org/W2997122788","https://openalex.org/W3033373331","https://openalex.org/W3112347997","https://openalex.org/W3135763546","https://openalex.org/W4289526978","https://openalex.org/W4299345493","https://openalex.org/W4383899664","https://openalex.org/W6639350448","https://openalex.org/W6678701371","https://openalex.org/W6737432229"],"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],"detection":[2],"(ASD)":[3],"crucially":[4],"prevents":[5],"industrial":[6],"accidents":[7],"by":[8,118],"distinguishing":[9],"normal":[10],"and":[11,19,112],"abnormal":[12],"machine":[13],"sounds.":[14],"Previous":[15],"research":[16],"utilizing":[17],"timbral":[18,59,111],"short-term":[20],"features":[21,114],"attained":[22],"a":[23,83],"notable":[24],"F1":[25],"score":[26],"of":[27,42,76],"0.920.":[28],"However,":[29],"relying":[30],"solely":[31],"on":[32,49],"supervised":[33],"learning":[34,53],"models":[35],"is":[36],"impractical":[37],"due":[38],"to":[39,73,89,121],"the":[40,95,104,122,126],"difficulty":[41],"acquiring":[43],"anomaly":[44],"data.":[45],"This":[46],"study":[47],"focuses":[48],"developing":[50],"an":[51],"unsupervised":[52],"model":[54],"for":[55],"ASD,":[56],"emphasizing":[57],"prominent":[58],"features.":[60],"We":[61,81],"also":[62],"investigate":[63],"human":[64,74],"voice":[65],"disorder":[66],"(HVD)-related":[67],"features,":[68],"which":[69],"are":[70],"potentially":[71],"linked":[72],"perception":[75],"anomalous":[77],"sounds":[78],"in":[79,125],"machines.":[80],"conducted":[82],"comparative":[84],"analysis":[85],"using":[86,110],"5-fold":[87],"cross-validation":[88],"evaluate":[90],"our":[91],"proposed":[92,107],"method,":[93],"with":[94],"area":[96],"under":[97],"receiver":[98],"operating":[99],"characteristic":[100],"(ROC":[101],"AUC)":[102],"as":[103],"metric.":[105],"The":[106],"ASD":[108],"method":[109],"HVD-related":[113],"significantly":[115],"improved":[116],"AUC":[117],"10.87%":[119],"compared":[120],"baseline":[123],"system":[124],"DCASE":[127],"Challenge":[128],"2020.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
