{"id":"https://openalex.org/W4408352515","doi":"https://doi.org/10.1109/icassp49660.2025.10888123","title":"ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds","display_name":"ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352515","doi":"https://doi.org/10.1109/icassp49660.2025.10888123"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888123","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/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":false,"raw_author_name":"Sreyan Ghosh","raw_affiliation_strings":["University of Maryland,College Park,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,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,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,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/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandra Kiran Reddy Evuru","raw_affiliation_strings":["Adobe Research,San Francisco,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research,San Francisco,CA,USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110542743","display_name":"Oriol Nieto","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oriol Nieto","raw_affiliation_strings":["Adobe Research,San Francisco,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research,San Francisco,CA,USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"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/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramani Duraiswami","raw_affiliation_strings":["Adobe Research,San Francisco,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research,San Francisco,CA,USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"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/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["Adobe Research,San Francisco,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research,San Francisco,CA,USA","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1921,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.90526954,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"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":0.9980000257492065,"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":0.9980000257492065,"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":0.9884999990463257,"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":0.9868999719619751,"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":0.7103734612464905},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5955885648727417},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5783879160881042},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5516654849052429}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7103734612464905},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5955885648727417},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5783879160881042},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5516654849052429},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888123","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2052666245","https://openalex.org/W2509065397","https://openalex.org/W2593116425","https://openalex.org/W3015371781","https://openalex.org/W3176445421","https://openalex.org/W3198452188","https://openalex.org/W4205689591","https://openalex.org/W4221157007","https://openalex.org/W4226442948","https://openalex.org/W4284898017","https://openalex.org/W4312097006","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4387969125","https://openalex.org/W4392903210","https://openalex.org/W4408352226","https://openalex.org/W4408353237","https://openalex.org/W6736723571","https://openalex.org/W6752516136","https://openalex.org/W6769627184","https://openalex.org/W6791353385","https://openalex.org/W6849105126","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6852818750","https://openalex.org/W6853249747","https://openalex.org/W6854866820","https://openalex.org/W6857657557","https://openalex.org/W6861859833"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Open-vocabulary":[0],"audio-language":[1],"models,":[2],"like":[3],"CLAP":[4,95],"[1],":[5],"offer":[6],"a":[7,34,74,94],"promising":[8],"approach":[9],"for":[10,102,164],"zero-shot":[11,140],"audio":[12,100,141],"classification":[13,17,142],"(ZSAC)":[14],"by":[15,197,204],"enabling":[16],"with":[18,25,42,54,98,143],"any":[19],"arbitrary":[20],"set":[21],"of":[22,51,60,105,155],"categories":[23],"specified":[24],"natural":[26],"language":[27],"prompts.":[28],"In":[29,149],"this":[30],"paper,":[31],"we":[32,45,90,145,160],"propose":[33,92,146],"simple":[35],"but":[36],"effective":[37],"method":[38,50,154,191],"to":[39,63,138,151],"improve":[40,139],"ZSAC":[41,196],"CLAP.":[43],"Specifically,":[44],"shift":[46],"from":[47],"the":[48,85,108,118,152,169,176,180],"conventional":[49],"using":[52,68,121],"prompts":[53,64,163,173],"abstract":[55],"category":[56],"labels":[57],"(e.g.,":[58,77],"Sound":[59],"an":[61],"organ)":[62],"that":[65],"describe":[66,113,175],"sounds":[67,106],"their":[69,122],"inherent":[70],"descriptive":[71],"features":[72],"in":[73,107,117,168,179,186],"diverse":[75,187],"context":[76],"The":[78],"organ\u2019s":[79],"deep":[80],"and":[81,135,182,199],"resonant":[82],"tones":[83],"filled":[84],"cathedral.).":[86],"To":[87],"achieve":[88],"this,":[89],"first":[91,174],"ReCLAP,":[93,144],"model":[96],"trained":[97],"rewritten":[99,111],"captions":[101,112],"improved":[103],"understanding":[104],"wild.":[109],"These":[110,171],"each":[114,165],"sound":[115,177],"event":[116,178],"original":[119],"caption":[120],"unique":[123,166],"discriminative":[124],"characteristics.":[125],"ReCLAP":[126],"outperforms":[127,200],"all":[128,202],"baselines":[129,203],"on":[130,195],"both":[131],"multi-modal":[132],"audio-text":[133],"retrieval":[134],"ZSAC.":[136],"Next,":[137],"prompt":[147],"augmentation.":[148],"contrast":[150],"traditional":[153],"employing":[156],"hand-written":[157],"template":[158],"prompts,":[159],"generate":[161],"custom":[162,172],"label":[167,181],"dataset.":[170],"then":[183],"employ":[184],"them":[185],"scenes.":[188],"Our":[189],"proposed":[190],"improves":[192],"ReCLAP\u2019s":[193],"performance":[194],"1%-18%":[198],"1":[201],"1%":[205],"-":[206],"55%<sup":[207],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[208],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}