{"id":"https://openalex.org/W4224917958","doi":"https://doi.org/10.1109/icassp43922.2022.9747863","title":"Self-Supervised Representation Learning for Unsupervised Anomalous Sound Detection Under Domain Shift","display_name":"Self-Supervised Representation Learning for Unsupervised Anomalous Sound Detection Under Domain Shift","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224917958","doi":"https://doi.org/10.1109/icassp43922.2022.9747863"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747863","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Self-Supervised_Representation_Learning_for_Unsupervised_Anomalous_Sound_Detection_Under_Domain_Shift/24217296","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100732644","display_name":"Han Chen","orcid":"https://orcid.org/0000-0002-3000-3152"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Chen","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Song","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","ICT Cluster, Singapore Institute of Technology, Singapore","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"ICT Cluster, Singapore Institute of Technology, Singapore","institution_ids":["https://openalex.org/I168639165"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100383322","display_name":"Lin Liu","orcid":"https://orcid.org/0000-0002-8919-3173"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Liu","raw_affiliation_strings":["iFLYTEK CO., LTD,iFLYTEK Research,Hefei,China","iFLYTEK Research, iFLYTEK CO., LTD, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK CO., LTD,iFLYTEK Research,Hefei,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK CO., LTD, Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"471","last_page":"475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9984999895095825,"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/T10860","display_name":"Speech and Audio Processing","score":0.9926000237464905,"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":0.7564761638641357},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7541007995605469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.589144229888916},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5748863816261292},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5434517860412598},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.44941481947898865},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.43468883633613586},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43303436040878296},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4162948727607727},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41520124673843384},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3792268633842468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7564761638641357},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7541007995605469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.589144229888916},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5748863816261292},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5434517860412598},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.44941481947898865},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.43468883633613586},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43303436040878296},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4162948727607727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41520124673843384},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3792268633842468},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747863","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/24217296","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Self-Supervised_Representation_Learning_for_Unsupervised_Anomalous_Sound_Detection_Under_Domain_Shift/24217296","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/24217296","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Self-Supervised_Representation_Learning_for_Unsupervised_Anomalous_Sound_Detection_Under_Domain_Shift/24217296","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2104657103","https://openalex.org/W2194775991","https://openalex.org/W2299668505","https://openalex.org/W2312004824","https://openalex.org/W2765407302","https://openalex.org/W2939422005","https://openalex.org/W2951883849","https://openalex.org/W2963163009","https://openalex.org/W2963870446","https://openalex.org/W2965433388","https://openalex.org/W2997739323","https://openalex.org/W3015356122","https://openalex.org/W3034883497","https://openalex.org/W3162150435","https://openalex.org/W3170230444","https://openalex.org/W4236333699","https://openalex.org/W4300833946","https://openalex.org/W4394662183","https://openalex.org/W6697673422","https://openalex.org/W6757615711","https://openalex.org/W6760184523","https://openalex.org/W6779961064","https://openalex.org/W6796250704","https://openalex.org/W6864909175"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W2355833770","https://openalex.org/W1985458517","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W2898649268","https://openalex.org/W4289752279"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,30,34,47,83,104,124,131,147],"self-supervised":[4,94],"representation":[5,126,165],"learning":[6,127],"method":[7],"is":[8,36,46,74,159],"proposed":[9,182],"for":[10,77,138,155,169],"anomalous":[11,37],"sound":[12,31,43,86,98],"detection":[13],"(ASD).":[14],"ASD":[15,137,175],"has":[16],"received":[17],"much":[18],"research":[19],"attention":[20,133],"in":[21],"recent":[22],"DCASE":[23],"challenges.":[24],"It":[25],"aims":[26],"to":[27,51,135],"identify":[28],"whether":[29],"emitted":[32],"from":[33,58],"machine":[35,60,69,140],"or":[38],"not,":[39],"given":[40,97],"only":[41,82],"normal":[42],"data.":[44],"This":[45,73,161],"challenging":[48],"task":[49,176],"due":[50],"highly":[52],"variable":[53],"time-frequency":[54,132],"characteristics":[55],"of":[56,93,106,114,180],"sounds":[57],"different":[59,119,139],"types,":[61],"and":[62,142,166],"the":[63,91,112,178,181],"fact":[64],"that":[65],"many":[66],"attributes":[67],"affect":[68],"without":[70],"being":[71],"anomalous.":[72],"especially":[75],"true":[76],"domain":[78,145,157],"shift":[79],"tasks,":[80],"where":[81,111],"few":[84],"training":[85],"clips":[87],"are":[88],"available.":[89],"From":[90],"perspective":[92],"learning,":[95],"each":[96,115],"clip":[99,116],"can":[100],"be":[101],"considered":[102],"as":[103],"transformation":[105],"an":[107,167],"original":[108],"clean":[109],"sound,":[110],"attribute":[113],"may":[117],"indicate":[118],"supervision":[120],"signals.":[121],"We":[122],"propose":[123],"unified":[125],"framework,":[128],"equipped":[129],"with":[130],"mechanism,":[134],"perform":[136],"types":[141],"attributes.":[143],"For":[144],"shift,":[146],"centre":[148],"imprinting":[149],"method,":[150],"which":[151],"directly":[152],"sets":[153],"centres":[154],"target":[156],"attributes,":[158],"presented.":[160],"provides":[162],"immediate":[163],"good":[164],"initialization":[168],"further":[170],"fine-tuning.":[171],"Evaluation":[172],"on":[173],"DCASE2021":[174],"demonstrates":[177],"effectiveness":[179],"method.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}