{"id":"https://openalex.org/W4406858412","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849056","title":"Self-Supervised Augmented Diffusion Model for Anomalous Sound Detection","display_name":"Self-Supervised Augmented Diffusion Model for Anomalous Sound Detection","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858412","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849056"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849056","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/A5084474343","display_name":"Jiawei Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiawei Yin","raw_affiliation_strings":["East China University of Science and Technology,Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education,Shanghai,China,200237"],"affiliations":[{"raw_affiliation_string":"East China University of Science and Technology,Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education,Shanghai,China,200237","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100710810","display_name":"Wenbin Zhang","orcid":"https://orcid.org/0000-0002-7681-7530"},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbin Zhang","raw_affiliation_strings":["Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702"],"affiliations":[{"raw_affiliation_string":"Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116479882","display_name":"Mingjun Zhang","orcid":"https://orcid.org/0000-0002-8090-5963"},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjun Zhang","raw_affiliation_strings":["Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702"],"affiliations":[{"raw_affiliation_string":"Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020803502","display_name":"Yu Gao","orcid":"https://orcid.org/0000-0002-2135-7872"},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Gao","raw_affiliation_strings":["Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702"],"affiliations":[{"raw_affiliation_string":"Midea Group (Shanghai) Co., Ltd.,AI Research Center,Shanghai,China,201702","institution_ids":["https://openalex.org/I4210093653"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084474343"],"corresponding_institution_ids":["https://openalex.org/I143593769"],"apc_list":null,"apc_paid":null,"fwci":0.7501,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73364386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"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":0.9427000284194946,"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":0.9427000284194946,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9296000003814697,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9294999837875366,"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":0.6087425947189331},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6033477187156677},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.568551242351532},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3844302296638489},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33142441511154175},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20460966229438782},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11044922471046448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6087425947189331},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6033477187156677},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.568551242351532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3844302296638489},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33142441511154175},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20460966229438782},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11044922471046448},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849056","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":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2752782242","https://openalex.org/W3130472073","https://openalex.org/W3201549834","https://openalex.org/W3215680118","https://openalex.org/W4221140395","https://openalex.org/W4224917958","https://openalex.org/W4225274992","https://openalex.org/W4292851291","https://openalex.org/W4297828509","https://openalex.org/W4312319569","https://openalex.org/W4372260076","https://openalex.org/W4372260191","https://openalex.org/W4388117975","https://openalex.org/W4390872231","https://openalex.org/W4392902665","https://openalex.org/W4392903041","https://openalex.org/W4392903511","https://openalex.org/W4392903829","https://openalex.org/W4392903901","https://openalex.org/W4394779406","https://openalex.org/W4399346504","https://openalex.org/W6779823529","https://openalex.org/W6852385146","https://openalex.org/W6869072782"],"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":{"Generative":[0],"models":[1,27],"have":[2],"significantly":[3],"enhanced":[4],"the":[5,37,48,105,111,123,131,136,143,148,157,160],"capability":[6],"of":[7,39,107,125,159],"unsupervised":[8],"anomalous":[9],"sound":[10,33],"detection":[11],"(ASD)":[12],"with":[13,89],"their":[14],"strong":[15],"data":[16,34,127],"modeling":[17],"capabilities.":[18],"However,":[19],"many":[20],"existing":[21],"ASD":[22,78,94],"methods":[23,52],"based":[24],"on":[25,30,147],"generative":[26],"focus":[28],"solely":[29],"accurately":[31],"reconstructing":[32],"itself,":[35],"neglecting":[36],"use":[38],"metadata.":[40],"This":[41],"results":[42],"in":[43,135],"limited":[44],"features":[45],"learned":[46],"by":[47,130],"models.":[49],"Additionally,":[50],"these":[51,66,108],"suffer":[53],"from":[54,122],"issues":[55],"such":[56],"as":[57,110,142],"low":[58],"generation":[59],"quality":[60],"and":[61,96],"mode":[62],"collapse.":[63],"To":[64],"address":[65],"challenges,":[67],"we":[68],"propose":[69],"a":[70,85,90,99],"self-supervised":[71,86,132],"augmented":[72],"diffusion":[73,101,138],"model":[74],"(SSDM)":[75],"to":[76,103],"improve":[77],"performance.":[79],"SSDM":[80],"learns":[81],"expressive":[82],"embeddings":[83,109,128],"through":[84],"learning":[87,133],"module":[88,102,134],"dual-path":[91],"time-frequency":[92],"self-attention":[93],"framework":[95],"then":[97],"uses":[98],"denoising":[100,137],"learn":[104],"distribution":[106],"basis":[112],"for":[113],"anomaly":[114,144],"detection.":[115],"The":[116],"reconstruction":[117,124],"loss,":[118],"which":[119],"is":[120,140],"derived":[121],"test":[126],"measured":[129],"module,":[139],"used":[141],"score.":[145],"Experiments":[146],"DCASE":[149],"Challenge":[150],"2023":[151],"Task":[152],"2":[153],"development":[154],"dataset":[155],"demonstrate":[156],"effectiveness":[158],"proposed":[161],"method.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}