{"id":"https://openalex.org/W4412708943","doi":"https://doi.org/10.1093/comjnl/bxaf087","title":"EDTC: enhanced depth of text comprehension in automated audio captioning","display_name":"EDTC: enhanced depth of text comprehension in automated audio captioning","publication_year":2025,"publication_date":"2025-07-24","ids":{"openalex":"https://openalex.org/W4412708943","doi":"https://doi.org/10.1093/comjnl/bxaf087"},"language":"en","primary_location":{"id":"doi:10.1093/comjnl/bxaf087","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxaf087","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-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/A5024665224","display_name":"Liwen Tan","orcid":"https://orcid.org/0000-0002-5451-9356"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liwen Tan","raw_affiliation_strings":["School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications , No. 2 Chongwen Road, Nan\u2019an District, Chongqing 400065 ,","School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, No. 2 Chongwen Road, Nan'an District, Chongqing 400065, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications , No. 2 Chongwen Road, Nan\u2019an District, Chongqing 400065 ,","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, No. 2 Chongwen Road, Nan'an District, Chongqing 400065, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101704070","display_name":"Yi Zhou","orcid":"https://orcid.org/0000-0002-3982-9145"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhou","raw_affiliation_strings":["School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications , No. 2 Chongwen Road, Nan\u2019an District, Chongqing 400065 ,","School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, No. 2 Chongwen Road, Nan'an District, Chongqing 400065, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications , No. 2 Chongwen Road, Nan\u2019an District, Chongqing 400065 ,","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, No. 2 Chongwen Road, Nan'an District, Chongqing 400065, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003114586","display_name":"Yin Liu","orcid":"https://orcid.org/0000-0002-4555-1944"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Liu","raw_affiliation_strings":["School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications , No. 2 Chongwen Road, Nan\u2019an District, Chongqing 400065 ,","School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, No. 2 Chongwen Road, Nan'an District, Chongqing 400065, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications , No. 2 Chongwen Road, Nan\u2019an District, Chongqing 400065 ,","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, No. 2 Chongwen Road, Nan'an District, Chongqing 400065, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101590005","display_name":"Yin Cao","orcid":"https://orcid.org/0000-0001-9086-7027"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Cao","raw_affiliation_strings":["Department of Intelligent Science, Xi\u2019an Jiaotong-Liverpool University , 111 Ren\u2019ai Road, Dushu Lake Science and Education Innovation District, Suzhou Industrial Park, Suzhou, Jiangsu 215123 ,","Department of Intelligent Science, Xi'an Jiaotong-Liverpool University, 111 Ren'ai Road, Dushu Lake Science and Education Innovation District, Suzhou Industrial Park, Suzhou, Jiangsu 215123, China"],"affiliations":[{"raw_affiliation_string":"Department of Intelligent Science, Xi\u2019an Jiaotong-Liverpool University , 111 Ren\u2019ai Road, Dushu Lake Science and Education Innovation District, Suzhou Industrial Park, Suzhou, Jiangsu 215123 ,","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"Department of Intelligent Science, Xi'an Jiaotong-Liverpool University, 111 Ren'ai Road, Dushu Lake Science and Education Innovation District, Suzhou Industrial Park, Suzhou, Jiangsu 215123, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024665224"],"corresponding_institution_ids":["https://openalex.org/I10535382"],"apc_list":{"value":2635,"currency":"GBP","value_usd":3232},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26402009,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"68","issue":"12","first_page":"1957","last_page":"1966"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9453949928283691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7899796962738037},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5174537301063538},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5043660402297974},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4741755723953247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3660880923271179},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34329378604888916},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1114446222782135},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.045864880084991455}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9453949928283691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7899796962738037},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5174537301063538},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5043660402297974},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4741755723953247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3660880923271179},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34329378604888916},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1114446222782135},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.045864880084991455}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/comjnl/bxaf087","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxaf087","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W2506483933","https://openalex.org/W2593116425","https://openalex.org/W2600463316","https://openalex.org/W2936774411","https://openalex.org/W2990138404","https://openalex.org/W2998529071","https://openalex.org/W3000491333","https://openalex.org/W3015591594","https://openalex.org/W3034999214","https://openalex.org/W3046194589","https://openalex.org/W3094550259","https://openalex.org/W3205860970","https://openalex.org/W4212807739","https://openalex.org/W4226178544","https://openalex.org/W4226442948","https://openalex.org/W4236965008","https://openalex.org/W4280567182","https://openalex.org/W4285306484","https://openalex.org/W4286488082","https://openalex.org/W4288391450","https://openalex.org/W4297841258","https://openalex.org/W4301409532","https://openalex.org/W4307933152","https://openalex.org/W4309130070","https://openalex.org/W4312089343","https://openalex.org/W4315631934","https://openalex.org/W4362014679","https://openalex.org/W4372266552","https://openalex.org/W4383340360","https://openalex.org/W4385822505","https://openalex.org/W4385822843","https://openalex.org/W4392903033","https://openalex.org/W4392903299","https://openalex.org/W4392909554","https://openalex.org/W4400033239","https://openalex.org/W6641064462","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6753850902","https://openalex.org/W6763563303","https://openalex.org/W6766818547","https://openalex.org/W6770717842","https://openalex.org/W6774314701","https://openalex.org/W6791353385","https://openalex.org/W6799494382","https://openalex.org/W6802577842","https://openalex.org/W6810938606","https://openalex.org/W6840389949","https://openalex.org/W6846664954","https://openalex.org/W6848208918","https://openalex.org/W6851317029","https://openalex.org/W6852818750","https://openalex.org/W6853168154","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Abstract":[0],"Modality":[1],"discrepancies":[2],"have":[3],"perpetually":[4],"posed":[5],"significant":[6],"challenges":[7],"within":[8],"the":[9,37,51,65,85,110,117,135,160,170],"realm":[10],"of":[11,40,80,88,112,119],"Automated":[12],"Audio":[13],"Captioning":[14],"(AAC)":[15],"and":[16,42,116,172],"across":[17,169],"all":[18],"multimodal":[19],"domains.":[20],"Facilitating":[21],"models":[22],"in":[23,31],"comprehending":[24],"text":[25,41,81,89,173],"information":[26,90,115],"plays":[27],"a":[28,33,96,124,130,145],"pivotal":[29],"role":[30],"establishing":[32],"seamless":[34],"connection":[35],"between":[36,53,67],"two":[38,55],"modalities":[39,56,69,143],"audio.":[43],"While":[44],"recent":[45],"research":[46],"has":[47],"focused":[48],"on":[49,134],"closing":[50],"gap":[52],"these":[54],"through":[57],"contrastive":[58,73,151],"learning,":[59],"it":[60],"is":[61,102,153],"challenging":[62],"to":[63,104,162],"bridge":[64],"difference":[66],"both":[68,142],"using":[70],"only":[71],"simple":[72],"loss.":[74],"This":[75],"paper":[76],"introduces":[77],"enhanced":[78],"depth":[79],"comprehension,":[82],"which":[83],"enhances":[84],"model\u2019s":[86],"understanding":[87],"from":[91,141],"three":[92],"different":[93],"perspectives.":[94],"First,":[95],"combined":[97],"Local-Global":[98],"feature":[99],"Fusion":[100],"module":[101],"introduced":[103],"fuse":[105],"heterogeneous":[106],"audio":[107,171],"features,":[108],"enabling":[109],"extraction":[111],"high-level":[113,166],"semantic":[114,167],"discovery":[118],"latent":[120],"inter-sample":[121],"relationships.":[122],"Next,":[123],"novel":[125],"representation":[126],"module,":[127],"TRANSLATOR,":[128],"constructs":[129],"twin-branch":[131],"structure":[132],"based":[133],"conventional":[136],"dual-stream":[137],"model,":[138],"mapping":[139],"features":[140],"into":[144],"shared":[146,165],"high-dimensional":[147],"audio-text":[148],"space.":[149],"Finally,":[150],"learning":[152],"integrated":[154],"with":[155],"momentum-based":[156],"weight":[157],"updates,":[158],"allowing":[159],"system":[161],"effectively":[163],"capture":[164],"representations":[168],"modalities.":[174]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}
