{"id":"https://openalex.org/W4406461830","doi":"https://doi.org/10.1109/slt61566.2024.10832335","title":"Improving Anomalous Sound Detection Via Low-Rank Adaptation Fine-Tuning of Pre-Trained Audio Models","display_name":"Improving Anomalous Sound Detection Via Low-Rank Adaptation Fine-Tuning of Pre-Trained Audio Models","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461830","doi":"https://doi.org/10.1109/slt61566.2024.10832335"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5062424202","display_name":"Xinhu Zheng","orcid":"https://orcid.org/0000-0002-9898-5543"},"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":true,"raw_author_name":"Xinhu Zheng","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032861798","display_name":"Anbai Jiang","orcid":null},"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":"Anbai Jiang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100690517","display_name":"Bing Han","orcid":"https://orcid.org/0000-0002-6319-6755"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Han","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artifcial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artifcial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artifcial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artifcial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079233004","display_name":"Pingyi Fan","orcid":"https://orcid.org/0000-0002-0658-6079"},"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":"Pingyi Fan","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"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":"Jia Liu","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"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":"Wei-Qiang Zhang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China"],"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":7,"corresponding_author_ids":["https://openalex.org/A5062424202"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.6339,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91351351,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"969","last_page":"974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.6735857725143433},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5732806921005249},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4921054244041443},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46047818660736084},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.44919490814208984},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.41512852907180786},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3294048011302948},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.27060914039611816},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.20712950825691223},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06665119528770447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6735857725143433},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5732806921005249},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4921054244041443},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46047818660736084},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.44919490814208984},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.41512852907180786},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3294048011302948},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.27060914039611816},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.20712950825691223},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06665119528770447},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2936774411","https://openalex.org/W2969985801","https://openalex.org/W3036601975","https://openalex.org/W3204701960","https://openalex.org/W3216154338","https://openalex.org/W4306955484","https://openalex.org/W4372260191","https://openalex.org/W4388718054","https://openalex.org/W4392902665","https://openalex.org/W4392903605","https://openalex.org/W4392904001","https://openalex.org/W4402111764","https://openalex.org/W6780218876","https://openalex.org/W6796581206","https://openalex.org/W6838495258","https://openalex.org/W6848208918","https://openalex.org/W6852385146","https://openalex.org/W6859099255","https://openalex.org/W6864909175"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2769884427","https://openalex.org/W2088690926","https://openalex.org/W2157165686","https://openalex.org/W2371215329","https://openalex.org/W1975359510"],"abstract_inverted_index":{"Anomalous":[0],"Sound":[1],"Detection":[2],"(ASD)":[3],"has":[4],"gained":[5],"significant":[6,128],"interest":[7],"through":[8],"the":[9,37,45,51,87,101,111,123,149,165,168],"application":[10],"of":[11,47,53,89,96,103,120,130,151,167],"various":[12],"Artificial":[13],"Intelligence":[14],"(AI)":[15],"technologies":[16],"in":[17,31],"industrial":[18],"settings.":[19],"Though":[20],"possessing":[21],"great":[22],"potential,":[23],"ASD":[24,61],"systems":[25],"can":[26],"hardly":[27],"be":[28],"readily":[29],"deployed":[30],"real":[32],"production":[33],"sites":[34],"due":[35],"to":[36,99,163],"generalization":[38],"problem,":[39],"which":[40,147],"is":[41],"primarily":[42],"caused":[43],"by":[44],"difficulty":[46],"data":[48,81,105],"collection":[49],"and":[50,143],"complexity":[52],"environmental":[54],"factors.":[55],"This":[56],"paper":[57],"introduces":[58],"a":[59,80,117,127],"robust":[60],"model":[62],"that":[63],"leverages":[64],"audio":[65,152],"pre-trained":[66,145,153],"models.":[67],"Specifically,":[68],"we":[69,85],"fine-tune":[70],"these":[71],"models":[72,154],"using":[73],"machine":[74],"operation":[75],"data,":[76],"employing":[77],"SpecAug":[78],"as":[79],"augmentation":[82],"strategy.":[83],"Additionally,":[84],"investigate":[86],"impact":[88],"utilizing":[90],"Low-Rank":[91],"Adaptation":[92],"(LoRA)":[93],"tuning":[94],"instead":[95],"full":[97],"fine-tuning":[98],"address":[100],"problem":[102],"limited":[104],"for":[106],"fine-tuning.":[107],"Our":[108],"experiments":[109],"on":[110,122],"DCASE2023":[112],"Task":[113],"2":[114],"dataset":[115],"establish":[116],"new":[118],"benchmark":[119],"77.75%":[121],"evaluation":[124],"set,":[125],"with":[126,133,155],"improvement":[129],"6.48%":[131],"compared":[132],"previous":[134],"state-of-the-art":[135],"(SOTA)":[136],"models,":[137,146],"including":[138],"top-tier":[139],"traditional":[140],"convolutional":[141],"networks":[142],"speech":[144],"demonstrates":[148],"effectiveness":[150],"LoRA":[156],"tuning.":[157],"Ablation":[158],"studies":[159],"are":[160],"also":[161],"conducted":[162],"showcase":[164],"efficacy":[166],"proposed":[169],"scheme.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}