{"id":"https://openalex.org/W4408354482","doi":"https://doi.org/10.1109/icassp49660.2025.10887974","title":"Deep Generic Representations for Domain-Generalized Anomalous Sound Detection","display_name":"Deep Generic Representations for Domain-Generalized Anomalous Sound Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354482","doi":"https://doi.org/10.1109/icassp49660.2025.10887974"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887974","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":"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/A5114352432","display_name":"Phurich Saengthong","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Phurich Saengthong","raw_affiliation_strings":["Tokyo Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","orcid":"https://orcid.org/0000-0001-8114-8450"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Shinozaki","raw_affiliation_strings":["Tokyo Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5114352432"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":4.7229,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93973455,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"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":0.9987999796867371,"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":0.9987999796867371,"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":0.9940999746322632,"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":0.9923999905586243,"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":0.6991114020347595},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5342904925346375},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5133694410324097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3866702914237976},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35522907972335815},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19961896538734436},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18507856130599976},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09874171018600464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6991114020347595},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5342904925346375},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5133694410324097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3866702914237976},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35522907972335815},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19961896538734436},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18507856130599976},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09874171018600464},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887974","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W153185079","https://openalex.org/W1554085250","https://openalex.org/W2593116425","https://openalex.org/W2982294822","https://openalex.org/W2997122788","https://openalex.org/W3015356122","https://openalex.org/W4200500401","https://openalex.org/W4221140395","https://openalex.org/W4372349138","https://openalex.org/W4388117975","https://openalex.org/W4392903829","https://openalex.org/W4392903901","https://openalex.org/W4402111764","https://openalex.org/W6739901393","https://openalex.org/W6757615711","https://openalex.org/W6779961064","https://openalex.org/W6784066080","https://openalex.org/W6784333009","https://openalex.org/W6796176086","https://openalex.org/W6838495258","https://openalex.org/W6848208918","https://openalex.org/W6852385146","https://openalex.org/W6864909175"],"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":{"Developing":[0],"a":[1,65,85,100,120],"reliable":[2],"anomalous":[3],"sound":[4],"detection":[5],"(ASD)":[6],"system":[7],"requires":[8],"robustness":[9,138],"to":[10,13,36,104],"noise,":[11],"adaptation":[12],"domain":[14,50,101],"shifts,":[15],"and":[16,110,136],"effective":[17],"performance":[18,46],"with":[19,72,99,125],"limited":[20,140],"training":[21],"data.":[22],"Current":[23],"leading":[24],"methods":[25],"rely":[26],"on":[27,47,131],"extensive":[28],"labeled":[29,123],"data":[30,124,141],"for":[31,74,80,88,122],"each":[32],"target":[33,49,91,111],"machine":[34],"type":[35],"train":[37],"feature":[38,62,69],"extractors":[39],"using":[40,94],"Outlier-Exposure":[41],"(OE)":[42],"techniques,":[43],"yet":[44],"their":[45],"the":[48,78,90,106,115,132],"remains":[51],"sub-optimal.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"present":[57],"Gen-Rep,":[58],"which":[59],"utilizes":[60],"generic":[61],"representations":[63],"from":[64],"robust,":[66],"large-scale":[67],"pre-trained":[68],"extractor":[70],"combined":[71],"kNN":[73],"domain-generalized":[75],"ASD,":[76],"without":[77,119],"need":[79,121],"fine-tuning.":[81],"GenRep":[82,113],"incorporates":[83],"MemMixup,":[84],"simple":[86],"approach":[87,118],"augmenting":[89],"memory":[92],"bank":[93],"nearest":[95],"source":[96,109],"samples,":[97],"paired":[98],"normalization":[102],"technique":[103],"address":[105],"imbalance":[107],"between":[108],"domains.":[112],"outperforms":[114],"best":[116],"OE-based":[117],"an":[126],"Official":[127],"Score":[128],"of":[129],"73.79%":[130],"DCASE2023T2":[133],"Eval":[134],"set":[135],"demonstrates":[137],"under":[139],"scenarios.":[142],"The":[143],"code":[144],"is":[145],"available":[146],"open-source":[147],"<sup":[148],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[149],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
