{"id":"https://openalex.org/W4392903210","doi":"https://doi.org/10.1109/icassp48485.2024.10448030","title":"Recap: Retrieval-Augmented Audio Captioning","display_name":"Recap: Retrieval-Augmented Audio Captioning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903210","doi":"https://doi.org/10.1109/icassp48485.2024.10448030"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5033408639","display_name":"Sreyan Ghosh","orcid":"https://orcid.org/0000-0003-3773-561X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sreyan Ghosh","raw_affiliation_strings":["University of Maryland,College Park,USA","University of Maryland, College Park, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101999829","display_name":"Sonal Kumar","orcid":"https://orcid.org/0009-0006-5516-3060"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sonal Kumar","raw_affiliation_strings":["University of Maryland,College Park,USA","University of Maryland, College Park, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092810058","display_name":"Chandra Kiran Reddy Evuru","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandra Kiran Reddy Evuru","raw_affiliation_strings":["University of Maryland,College Park,USA","University of Maryland, College Park, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013222310","display_name":"Ramani Duraiswami","orcid":"https://orcid.org/0000-0002-5596-8460"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramani Duraiswami","raw_affiliation_strings":["University of Maryland,College Park,USA","University of Maryland, College Park, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland,College Park,USA","University of Maryland, College Park, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5033408639"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":5.5284,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.96554831,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1161","last_page":"1165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9944999814033508,"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":0.9912999868392944,"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/closed-captioning","display_name":"Closed captioning","score":0.9408911466598511},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8490495681762695},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7339320182800293},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5651548504829407},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5365557670593262},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5196048617362976},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4593425691127777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36447399854660034},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36104196310043335},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3567849397659302},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12945279479026794}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9408911466598511},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8490495681762695},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7339320182800293},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5651548504829407},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5365557670593262},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5196048617362976},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4593425691127777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36447399854660034},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36104196310043335},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3567849397659302},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12945279479026794},{"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2252136820","https://openalex.org/W2912924812","https://openalex.org/W3015591594","https://openalex.org/W3027879771","https://openalex.org/W3034999214","https://openalex.org/W3112467147","https://openalex.org/W3122335742","https://openalex.org/W3160577380","https://openalex.org/W3185739472","https://openalex.org/W3187963534","https://openalex.org/W4210913346","https://openalex.org/W4226069413","https://openalex.org/W4226174231","https://openalex.org/W4303444943","https://openalex.org/W4372260310","https://openalex.org/W4372340819","https://openalex.org/W4377086529","https://openalex.org/W4386566587","https://openalex.org/W6691476020","https://openalex.org/W6777615688","https://openalex.org/W6787564935","https://openalex.org/W6798955355","https://openalex.org/W6810271737","https://openalex.org/W6811156277"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W2993670781"],"abstract_inverted_index":{"We":[0],"present":[1],"RECAP":[2,117,145],"(REtrieval-Augmented":[3],"Audio":[4],"CAPtioning),":[5],"a":[6,30,50,70,79,87,137,142],"novel":[7,151],"and":[8,21,90,98,113,124,158,181],"effective":[9],"audio":[10,20,27,54,103,152],"captioning":[11,150],"system":[12],"that":[13,116],"generates":[14],"captions":[15,23,65,177],"conditioned":[16],"on":[17,108],"an":[18,53,58],"input":[19],"other":[22],"similar":[24,66],"to":[25,38,63,67,77,86,100,132,135],"the":[26,42,95,102],"retrieved":[28],"from":[29,69],"datastore.":[31],"Additionally,":[32,130],"our":[33],"proposed":[34],"method":[35],"can":[36],"transfer":[37],"any":[39,45],"domain":[40],"without":[41],"need":[43],"for":[44,52,104,178],"additional":[46],"fine-tuning.":[47],"To":[48,164],"generate":[49],"caption":[51,105],"sample,":[55],"we":[56,82,170],"leverage":[57],"audio-text":[59],"model":[60],"CLAP":[61,96],"[1]":[62],"retrieve":[64],"it":[68],"replaceable":[71],"datastore,":[72],"which":[73],"are":[74],"then":[75],"used":[76],"construct":[78],"prompt.":[80],"Next,":[81],"feed":[83],"this":[84,168],"prompt":[85],"GPT-2":[88,99],"decoder":[89],"introduce":[91],"cross-attention":[92],"layers":[93],"between":[94],"encoder":[97],"condition":[101],"generation.":[106],"Experiments":[107],"two":[109],"benchmark":[110],"datasets,":[111],"Clotho":[112,182],"AudioCaps,":[114,180],"show":[115],"achieves":[118],"competitive":[119],"performance":[120],"in":[121,127,141,167],"in-domain":[122],"settings":[123],"significant":[125],"improvements":[126],"out-of-domain":[128],"settings.":[129],"due":[131],"its":[133],"capability":[134],"exploit":[136],"large":[138],"text-captions-only":[139],"datastore":[140],"training-free":[143],"fashion,":[144],"shows":[146],"unique":[147],"capabilities":[148],"of":[149],"events":[153],"never":[154],"seen":[155],"during":[156],"training":[157],"compositional":[159],"audios":[160],"with":[161],"multiple":[162],"events.":[163],"promote":[165],"research":[166],"space,":[169],"also":[171],"release":[172],"150,000+":[173],"new":[174],"weakly":[175],"labeled":[176],"AudioSet,":[179],"<sup":[183],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[184],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[185],".":[186]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
