{"id":"https://openalex.org/W4205830281","doi":"https://doi.org/10.23919/eusipco54536.2021.9615923","title":"Self-supervised Complex Network for Machine Sound Anomaly Detection","display_name":"Self-supervised Complex Network for Machine Sound Anomaly Detection","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4205830281","doi":"https://doi.org/10.23919/eusipco54536.2021.9615923"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9615923","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9615923","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5066878875","display_name":"Miseul Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Miseul Kim","raw_affiliation_strings":["Dept. of E.E., DSP&AI Lab., Yonsei Univ., Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Dept. of E.E., DSP&AI Lab., Yonsei Univ., Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013462104","display_name":"Minh Tri Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minh Tri Ho","raw_affiliation_strings":["Dept. of E.E., DSP&AI Lab., Yonsei Univ., Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Dept. of E.E., DSP&AI Lab., Yonsei Univ., Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Dept. of E.E., DSP&AI Lab., Yonsei Univ., Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Dept. of E.E., DSP&AI Lab., Yonsei Univ., Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066878875"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":1.2042,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86030893,"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":"586","last_page":"590"},"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":0.9995999932289124,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7311745882034302},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5818403363227844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5365474224090576},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.5255419611930847},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5028218626976013},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5010414123535156},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.4805179536342621},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3634147644042969},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3524094223976135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7311745882034302},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5818403363227844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5365474224090576},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5255419611930847},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5028218626976013},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5010414123535156},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.4805179536342621},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3634147644042969},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3524094223976135},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9615923","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9615923","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1556024794","https://openalex.org/W1601124178","https://openalex.org/W2070126272","https://openalex.org/W2076608692","https://openalex.org/W2105497548","https://openalex.org/W2144301583","https://openalex.org/W2337344967","https://openalex.org/W2574572704","https://openalex.org/W2606176153","https://openalex.org/W2620661538","https://openalex.org/W2755148105","https://openalex.org/W2786088545","https://openalex.org/W2947797412","https://openalex.org/W2949756029","https://openalex.org/W2952838738","https://openalex.org/W2963163009","https://openalex.org/W2982294822","https://openalex.org/W3021561894","https://openalex.org/W3023308054","https://openalex.org/W3034883497","https://openalex.org/W3095247787","https://openalex.org/W3096408984","https://openalex.org/W4298289240","https://openalex.org/W4300672471","https://openalex.org/W6633310491","https://openalex.org/W6639317949","https://openalex.org/W6736723571","https://openalex.org/W6748102297","https://openalex.org/W6757632829"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2743976221"],"abstract_inverted_index":{"In":[0,135],"this":[1],"paper,":[2],"we":[3,69,138],"propose":[4],"an":[5,43,72,117,143],"anomaly":[6],"detection":[7],"algorithm":[8,37,170],"for":[9,29],"machine":[10,67,90,104],"sounds":[11,110],"with":[12,162],"a":[13,98,158,172],"deep":[14],"complex":[15,40,47,81],"network":[16,95],"trained":[17,126],"by":[18],"self-supervision.":[19],"Using":[20],"the":[21,39,51,55,64,77,80,89,103,125,133,140,146,151,163,168,177],"fact":[22],"that":[23,101,167],"phase":[24,58],"continuity":[25],"information":[26,59],"is":[27,120,128,155],"crucial":[28],"detecting":[30],"abnormalities":[31],"in":[32],"time-series":[33],"signals,":[34],"our":[35,94],"proposed":[36,169],"utilizes":[38],"spectrum":[41,84],"as":[42,122],"input":[44,109,118],"and":[45,82],"performs":[46],"number":[48],"arithmetic":[49],"throughout":[50],"entire":[52],"process.":[53],"Since":[54],"usefulness":[56],"of":[57,66,79,107,142,150],"can":[60],"vary":[61],"depending":[62,87],"on":[63,88],"type":[65],"sound,":[68],"also":[70],"apply":[71],"attention":[73],"mechanism":[74],"to":[75,96,130],"control":[76],"weights":[78],"magnitude":[83,183],"bottleneck":[85],"features":[86],"type.":[91],"We":[92],"train":[93],"perform":[97],"self-supervised":[99],"task":[100,154],"classifies":[102],"identifier":[105],"(id)":[106],"normal":[108],"among":[111],"multiple":[112],"classes.":[113],"At":[114],"test":[115],"time,":[116],"signal":[119],"detected":[121],"anomalous":[123],"if":[124],"model":[127],"unable":[129],"correctly":[131],"classify":[132],"id.":[134],"other":[136],"words,":[137],"determine":[139],"presence":[141],"anomality":[144],"when":[145],"output":[147],"cross-entropy":[148],"score":[149,180],"multiclass":[152],"identification":[153],"lower":[156],"than":[157,181],"pre-defined":[159],"threshold.":[160],"Experiments":[161],"MIMII":[164],"dataset":[165],"show":[166],"has":[171],"much":[173],"higher":[174],"area":[175],"under":[176],"curve":[178],"(AUC)":[179],"conventional":[182],"spectrum-based":[184],"algorithms.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}