{"id":"https://openalex.org/W4408355866","doi":"https://doi.org/10.1109/icassp49660.2025.10888995","title":"Noise Supervised Contrastive Learning and Feature-Perturbed for Anomalous Sound Detection","display_name":"Noise Supervised Contrastive Learning and Feature-Perturbed for Anomalous Sound Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355866","doi":"https://doi.org/10.1109/icassp49660.2025.10888995"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888995","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":"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/A5102757710","display_name":"Shun Huang","orcid":"https://orcid.org/0009-0001-3012-7833"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shun Huang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000449705","display_name":"Zhihua Fang","orcid":"https://orcid.org/0000-0002-3018-7414"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Fang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049944728","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-4076-7479"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.5391,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97476704,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"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":0.9937999844551086,"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":0.9937999844551086,"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":0.9912999868392944,"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":0.988099992275238,"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":0.6582031846046448},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5985945463180542},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5719575881958008},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5448309779167175},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5375086665153503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5058090686798096},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4422939717769623},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4373888373374939},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2611715495586395},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12345448136329651},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0820314884185791},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06201395392417908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6582031846046448},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5985945463180542},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5719575881958008},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5448309779167175},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5375086665153503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5058090686798096},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4422939717769623},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4373888373374939},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2611715495586395},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12345448136329651},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0820314884185791},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06201395392417908},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888995","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":[{"score":0.46000000834465027,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W153185079","https://openalex.org/W2148154194","https://openalex.org/W2897802972","https://openalex.org/W2963976704","https://openalex.org/W2969985801","https://openalex.org/W2982294822","https://openalex.org/W2997122788","https://openalex.org/W3015356122","https://openalex.org/W3094550259","https://openalex.org/W3162150435","https://openalex.org/W4221140395","https://openalex.org/W4372260076","https://openalex.org/W4372260191","https://openalex.org/W4385245566","https://openalex.org/W4385822679","https://openalex.org/W4388117975","https://openalex.org/W4392902665","https://openalex.org/W4392903041","https://openalex.org/W4402111764","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6733814495","https://openalex.org/W6757817989","https://openalex.org/W6776700526","https://openalex.org/W6779961064","https://openalex.org/W6784066080","https://openalex.org/W6848208918"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W611303608","https://openalex.org/W4313595395","https://openalex.org/W2312783472","https://openalex.org/W2909748163"],"abstract_inverted_index":{"Unsupervised":[0],"anomalous":[1,8,117],"sound":[2,118],"detection":[3],"aims":[4],"to":[5],"detect":[6],"unknown":[7],"sounds":[9],"by":[10,60],"training":[11,47],"a":[12,45,69,97],"model":[13],"using":[14,92],"only":[15,93],"normal":[16],"audio":[17],"data.":[18],"Despite":[19],"advancements":[20],"in":[21,63],"self-supervised":[22],"methods,":[23],"the":[24,34,64,77],"issue":[25],"of":[26,33],"frequent":[27],"false":[28],"alarms":[29],"when":[30],"handling":[31],"samples":[32],"same":[35],"type":[36],"from":[37,107],"different":[38],"machines":[39],"remains":[40],"unresolved.":[41],"This":[42,110],"paper":[43],"introduces":[44],"novel":[46],"technique":[48],"called":[49],"one-stage":[50,70],"supervised":[51,72],"contrastive":[52,73],"learning":[53,74],"(OS-SCL),":[54],"which":[55,104],"significantly":[56],"addresses":[57],"this":[58],"problem":[59],"perturbing":[61],"features":[62],"embedding":[65],"space":[66],"and":[67,89,126],"employing":[68],"noisy":[71],"approach.":[75],"On":[76],"DCASE":[78],"2020":[79],"Challenge":[80],"Task":[81],"2,":[82],"it":[83],"achieved":[84],"94.64%":[85],"AUC,":[86,123],"88.42%":[87],"pAUC,":[88,125],"89.24%":[90],"mAUC":[91],"Log-Mel":[94],"features.":[95],"Additionally,":[96],"time-frequency":[98],"feature":[99,111],"named":[100],"TFgram":[101],"is":[102,105,132],"proposed,":[103],"extracted":[106],"raw":[108],"audio.":[109],"effectively":[112],"captures":[113],"critical":[114],"information":[115],"for":[116],"detection,":[119],"ultimately":[120],"achieving":[121],"95.71%":[122],"90.23%":[124],"91.23%":[127],"mAUC.":[128],"The":[129],"source":[130],"code":[131],"available":[133],"at:":[134],"www.github.com/huangswt/OS-SCL.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}