{"id":"https://openalex.org/W4372349649","doi":"https://doi.org/10.1109/icassp49357.2023.10095736","title":"Zero-Shot Anomalous Sound Detection in Domestic Environments Using Large-Scale Pretrained Audio Pattern Recognition Models","display_name":"Zero-Shot Anomalous Sound Detection in Domestic Environments Using Large-Scale Pretrained Audio Pattern Recognition Models","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372349649","doi":"https://doi.org/10.1109/icassp49357.2023.10095736"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095736","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5000588289","display_name":"Alessandro Ilic Mezza","orcid":"https://orcid.org/0000-0002-9438-3190"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Ilic Mezza","raw_affiliation_strings":["Politecnico di Milano,Milan,Italy,20133"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Milan,Italy,20133","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019738382","display_name":"Giulio Zanetti","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giulio Zanetti","raw_affiliation_strings":["Politecnico di Milano,Milan,Italy,20133"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Milan,Italy,20133","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089104482","display_name":"M\u00e1ximo Cobos","orcid":"https://orcid.org/0000-0001-7318-3192"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maximo Cobos","raw_affiliation_strings":["Universitat de Val&#x00E8;ncia,Burjassot, Val&#x00E8;ncia,Spain,46100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat de Val&#x00E8;ncia,Burjassot, Val&#x00E8;ncia,Spain,46100","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082156387","display_name":"Fabio Antonacci","orcid":"https://orcid.org/0000-0003-4545-0315"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Antonacci","raw_affiliation_strings":["Politecnico di Milano,Milan,Italy,20133"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Milan,Italy,20133","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.739,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68336016,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"20","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":0.9994000196456909,"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":0.9994000196456909,"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":0.9977999925613403,"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":0.9945999979972839,"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":0.786687970161438},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.7058855891227722},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5652443766593933},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.5326442718505859},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5260013341903687},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5051482319831848},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4598219692707062},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.4522937536239624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4485357403755188},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.4361829459667206},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.43010714650154114},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42282694578170776},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13807031512260437},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09749534726142883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786687970161438},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.7058855891227722},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5652443766593933},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.5326442718505859},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5260013341903687},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5051482319831848},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4598219692707062},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.4522937536239624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4485357403755188},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.4361829459667206},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.43010714650154114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42282694578170776},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13807031512260437},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09749534726142883},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095736","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1250202","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1250202","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1844944916","https://openalex.org/W1951755352","https://openalex.org/W2122646361","https://openalex.org/W2135131618","https://openalex.org/W2473930607","https://openalex.org/W2593116425","https://openalex.org/W2775505379","https://openalex.org/W2897802972","https://openalex.org/W2903442965","https://openalex.org/W2938728536","https://openalex.org/W2959539607","https://openalex.org/W3015205011","https://openalex.org/W3015622757","https://openalex.org/W3015898873","https://openalex.org/W3034883497","https://openalex.org/W3037001229","https://openalex.org/W3038482565","https://openalex.org/W3040266635","https://openalex.org/W3094550259","https://openalex.org/W3121952123","https://openalex.org/W3135550350","https://openalex.org/W3163309075","https://openalex.org/W4200337780","https://openalex.org/W4287751198","https://openalex.org/W4394662183","https://openalex.org/W6734260513","https://openalex.org/W6747331233","https://openalex.org/W6779961064","https://openalex.org/W6864909175"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W1983552326"],"abstract_inverted_index":{"Anomalous":[0],"sound":[1,86],"detection":[2],"is":[3,36,78,110,140],"central":[4],"to":[5,19,39,80,112],"audio-based":[6],"surveillance":[7],"and":[8,25,105,139],"monitoring.":[9],"In":[10],"a":[11,41,55,82],"domestic":[12],"environment,":[13],"however,":[14],"the":[15,32,46,90,101,106,116,119,129,135],"classes":[16],"of":[17,70,118,142],"sounds":[18],"be":[20,27],"considered":[21],"anomalous":[22],"are":[23,94],"situation-dependent":[24],"cannot":[26],"determined":[28],"in":[29,68],"advance.":[30],"At":[31],"same":[33],"time,":[34],"it":[35],"not":[37],"feasible":[38],"expect":[40],"demanding":[42],"labeling":[43],"effort":[44],"from":[45,100],"end":[47],"user.":[48,91],"To":[49],"address":[50],"these":[51],"problems,":[52],"we":[53],"present":[54],"novel":[56],"zero-shot":[57],"method":[58,131],"relying":[59],"on":[60,124],"an":[61,71],"auxiliary":[62,76],"large-scale":[63],"pretrained":[64],"audio":[65,103],"neural":[66],"network":[67],"support":[69],"unsupervised":[72,136],"anomaly":[73],"detector.":[74,121],"The":[75],"module":[77],"tasked":[79],"generate":[81],"fingerprint":[83],"for":[84,149],"each":[85],"occasionally":[87],"registered":[88],"by":[89],"These":[92],"fingerprints":[93],"then":[95],"compared":[96],"with":[97],"those":[98],"extracted":[99],"input":[102],"stream,":[104],"resulting":[107],"similarity":[108],"score":[109],"used":[111],"increase":[113],"or":[114],"reduce":[115],"sensitivity":[117],"base":[120,137],"Experimental":[122],"results":[123],"synthetic":[125],"data":[126],"show":[127],"that":[128],"proposed":[130],"substantially":[132],"improves":[133],"upon":[134],"detector":[138],"capable":[141],"outperforming":[143],"existing":[144],"few-shot":[145],"learning":[146],"systems":[147],"developed":[148],"machine":[150],"condition":[151],"monitoring":[152],"without":[153],"involving":[154],"additional":[155],"training.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
