{"id":"https://openalex.org/W4416798415","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249188","title":"Retrieval-Augmented Difference Captioning to Explain Unsupervised Anomalous Sound Detection","display_name":"Retrieval-Augmented Difference Captioning to Explain Unsupervised Anomalous Sound Detection","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798415","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249188"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5077630296","display_name":"Rei Ogura","orcid":null},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryoya Ogura","raw_affiliation_strings":["Research and Development Group, Hitachi, Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Development Group, Hitachi, Ltd","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040972515","display_name":"Tomoya Nishida","orcid":"https://orcid.org/0000-0002-1969-2268"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoya Nishida","raw_affiliation_strings":["Research and Development Group, Hitachi, Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Development Group, Hitachi, Ltd","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032619330","display_name":"Yohei Kawaguchi","orcid":"https://orcid.org/0000-0002-1027-5038"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yohei Kawaguchi","raw_affiliation_strings":["Research and Development Group, Hitachi, Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Development Group, Hitachi, Ltd","institution_ids":["https://openalex.org/I65143321"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I65143321"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38438635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.6068999767303467,"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":0.6068999767303467,"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":0.15620000660419464,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.02969999983906746,"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/closed-captioning","display_name":"Closed captioning","score":0.7095999717712402},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6348000168800354},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5238999724388123},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5142999887466431},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47609999775886536},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4478999972343445}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7095999717712402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.695900022983551},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6348000168800354},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5805000066757202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5318999886512756},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5142999887466431},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3280999958515167},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2779435589","wikidata":"https://www.wikidata.org/wiki/Q967103","display_name":"Heart sounds","level":2,"score":0.27709999680519104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":13,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2897802972","https://openalex.org/W2982294822","https://openalex.org/W2997122788","https://openalex.org/W3015356122","https://openalex.org/W3094550259","https://openalex.org/W4226442948","https://openalex.org/W4372260310","https://openalex.org/W4392902665","https://openalex.org/W4392903210","https://openalex.org/W4392903801","https://openalex.org/W4392903829","https://openalex.org/W4400033239"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,79,147],"method":[4,77],"for":[5,44,54,69,89,122],"generating":[6],"explanatory":[7],"captions":[8,38,153],"that":[9],"describe":[10],"how":[11],"sounds":[12,53,65,108,125],"identified":[13,109],"as":[14,110],"anomalous":[15,18,52,64,137],"in":[16],"unsupervised":[17],"sound":[19],"detection":[20,30,98],"(UASD)":[21],"differ":[22],"from":[23,81],"normal":[24,50,124,139],"sounds.":[25,140],"In":[26],"previous":[27],"methods,":[28],"anomaly":[29],"and":[31,51,92,99,101,126,138,146],"caption":[32,93,103],"generation":[33,104,115],"are":[34,66],"performed":[35],"independently,":[36],"so":[37],"may":[39],"not":[40,67],"reflect":[41],"the":[42,75,82,119,131,134,151,155,158],"reasons":[43],"detection.":[45],"Furthermore,":[46],"it":[47,57],"requires":[48],"paired":[49],"training,":[55],"making":[56],"impossible":[58],"to":[59,61,117],"apply":[60],"UASD,":[62],"where":[63],"available":[68],"training.":[70,106],"To":[71],"address":[72],"these":[73],"challenges,":[74],"proposed":[76,159],"utilizes":[78],"feature":[80],"pre-trained":[83],"CLAP":[84],"(Contrastive":[85],"Language-Audio":[86],"Pre-training)":[87],"model":[88],"both":[90],"UASD":[91],"generation,":[94],"ensuring":[95],"consistency":[96],"between":[97,136],"explanation,":[100],"enabling":[102],"without":[105],"For":[107],"anomalous,":[111],"we":[112],"use":[113],"retrieval-augmented":[114],"(RAG)":[116],"search":[118],"training":[120],"data":[121],"similar":[123],"compare":[127],"captions.":[128],"RAG":[129],"enables":[130],"capture":[132],"of":[133,150,157],"differences":[135],"Experiments":[141],"based":[142],"on":[143],"subjective":[144],"evaluation":[145],"sample-wise":[148],"analysis":[149],"output":[152],"demonstrate":[154],"effectiveness":[156],"method.":[160]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}