{"id":"https://openalex.org/W4392902953","doi":"https://doi.org/10.1109/icassp48485.2024.10446672","title":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","display_name":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902953","doi":"https://doi.org/10.1109/icassp48485.2024.10446672"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446672","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/A5101501437","display_name":"Jaeyeon Kim","orcid":"https://orcid.org/0000-0002-5196-3101"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210113560","display_name":"MDA Engineering (United States)","ror":"https://ror.org/01yeg0z60","country_code":"US","type":"company","lineage":["https://openalex.org/I4210113560"]}],"countries":["KR","US"],"is_corresponding":true,"raw_author_name":"Jaeyeon Kim","raw_affiliation_strings":["MAUM AI Inc.,Republic of Korea","MAUM AI Inc., Republic of Korea","Seoul National University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"MAUM AI Inc.,Republic of Korea","institution_ids":["https://openalex.org/I4210113560"]},{"raw_affiliation_string":"MAUM AI Inc., Republic of Korea","institution_ids":[]},{"raw_affiliation_string":"Seoul National University, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048369297","display_name":"Jae\u2010Yoon Jung","orcid":"https://orcid.org/0000-0002-4850-6284"},"institutions":[{"id":"https://openalex.org/I4210113560","display_name":"MDA Engineering (United States)","ror":"https://ror.org/01yeg0z60","country_code":"US","type":"company","lineage":["https://openalex.org/I4210113560"]},{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Jaeyoon Jung","raw_affiliation_strings":["MAUM AI Inc.,Republic of Korea","MAUM AI Inc., Republic of Korea","Soongsil University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"MAUM AI Inc.,Republic of Korea","institution_ids":["https://openalex.org/I4210113560"]},{"raw_affiliation_string":"MAUM AI Inc., Republic of Korea","institution_ids":[]},{"raw_affiliation_string":"Soongsil University, Republic of Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108898329","display_name":"Jinjoo Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113560","display_name":"MDA Engineering (United States)","ror":"https://ror.org/01yeg0z60","country_code":"US","type":"company","lineage":["https://openalex.org/I4210113560"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinjoo Lee","raw_affiliation_strings":["MAUM AI Inc.,Republic of Korea","MAUM AI Inc., Republic of Korea"],"affiliations":[{"raw_affiliation_string":"MAUM AI Inc.,Republic of Korea","institution_ids":["https://openalex.org/I4210113560"]},{"raw_affiliation_string":"MAUM AI Inc., Republic of Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066846974","display_name":"Sang Hoon Woo","orcid":"https://orcid.org/0000-0002-8805-3443"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sang Hoon Woo","raw_affiliation_strings":["Independent Researcher"],"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101501437"],"corresponding_institution_ids":["https://openalex.org/I139264467","https://openalex.org/I4210113560"],"apc_list":null,"apc_paid":null,"fwci":5.597,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.96624271,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6735","last_page":"6739"},"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":0.9969000220298767,"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":0.9958000183105469,"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":0.799973726272583},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7656762003898621},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7326022386550903},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6538859605789185},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6233043074607849},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5378406047821045},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5377329587936401},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.47725316882133484},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46858805418014526},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4683603048324585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4001137614250183},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16500124335289001},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.11849817633628845},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09423020482063293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.799973726272583},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7656762003898621},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7326022386550903},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6538859605789185},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6233043074607849},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5378406047821045},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5377329587936401},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.47725316882133484},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46858805418014526},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4683603048324585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4001137614250183},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16500124335289001},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.11849817633628845},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09423020482063293},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446672","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1889081078","https://openalex.org/W1956340063","https://openalex.org/W2123301721","https://openalex.org/W2506483933","https://openalex.org/W2593116425","https://openalex.org/W2949376505","https://openalex.org/W2964213897","https://openalex.org/W3015591594","https://openalex.org/W3034999214","https://openalex.org/W3094550259","https://openalex.org/W3097791920","https://openalex.org/W3103022576","https://openalex.org/W3112467147","https://openalex.org/W3206857696","https://openalex.org/W4221153784","https://openalex.org/W4226442948","https://openalex.org/W4297841258","https://openalex.org/W4307323391","https://openalex.org/W4307933152","https://openalex.org/W4312443924","https://openalex.org/W4364373974","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4372340819","https://openalex.org/W4377372369","https://openalex.org/W4379251221","https://openalex.org/W4385823080","https://openalex.org/W4388117700","https://openalex.org/W4400033239","https://openalex.org/W6639432524","https://openalex.org/W6678262379","https://openalex.org/W6787564935","https://openalex.org/W6798955355","https://openalex.org/W6802577842","https://openalex.org/W6811156277","https://openalex.org/W6846664954","https://openalex.org/W6850843143","https://openalex.org/W6852818750"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W2129913000","https://openalex.org/W2374470469","https://openalex.org/W2352448339","https://openalex.org/W2787189739","https://openalex.org/W2899318368","https://openalex.org/W3095556352","https://openalex.org/W2159899134","https://openalex.org/W2363660481"],"abstract_inverted_index":{"We":[0,26],"propose":[1],"EnCLAP,":[2],"a":[3,21,29],"novel":[4],"framework":[5],"for":[6],"automated":[7],"audio":[8],"captioning.":[9],"EnCLAP":[10],"employs":[11],"two":[12],"acoustic":[13,39],"representation":[14],"models,":[15],"EnCodec":[16],"and":[17,50],"CLAP,":[18],"along":[19],"with":[20],"pretrained":[22,43],"language":[23,44],"model,":[24],"BART.":[25],"also":[27],"introduce":[28],"new":[30],"training":[31],"objective":[32],"called":[33],"masked":[34],"codec":[35],"modeling":[36],"that":[37,53],"improves":[38],"awareness":[40],"of":[41,59],"the":[42,57],"model.":[45],"Experimental":[46],"results":[47],"on":[48],"AudioCaps":[49],"Clotho":[51],"demonstrate":[52],"our":[54],"model":[55],"surpasses":[56],"performance":[58],"baseline":[60],"models.":[61],"Source":[62],"code":[63],"will":[64],"be":[65],"available":[66],"at":[67],"https://github.com/jaeyeonkim99/EnCLAP.":[68],"<sup":[69],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[70],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[71]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}