{"id":"https://openalex.org/W4408353237","doi":"https://doi.org/10.1109/icassp49660.2025.10889473","title":"Sound-VECaps: Improving Audio Generation with Visually Enhanced Captions","display_name":"Sound-VECaps: Improving Audio Generation with Visually Enhanced Captions","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353237","doi":"https://doi.org/10.1109/icassp49660.2025.10889473"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889473","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/A5101889011","display_name":"Yi Yuan","orcid":"https://orcid.org/0000-0002-7121-0983"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Yi Yuan","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060687079","display_name":"Dongya Jia","orcid":"https://orcid.org/0000-0002-6307-8580"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongya Jia","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001776951","display_name":"Xiaobin Zhuang","orcid":"https://orcid.org/0000-0002-0285-6705"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaobin Zhuang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055175414","display_name":"Yuanzhe Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanzhe Chen","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620754","display_name":"Zhuo Chen","orcid":"https://orcid.org/0009-0003-2834-8789"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuping Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuping Wang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102840410","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0009-0003-2117-7059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407730","display_name":"Xubo Liu","orcid":"https://orcid.org/0009-0004-9950-2672"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108839490","display_name":"Xiyuan Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Xiyuan Kang","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5101889011"],"corresponding_institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"],"apc_list":null,"apc_paid":null,"fwci":62.0266,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.99845299,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9861999750137329,"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"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9861999750137329,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9189000129699707,"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":0.747211217880249},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5024967193603516},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46270138025283813},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.41551411151885986},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3306643068790436},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2927147448062897},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.238111674785614},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.20317047834396362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.747211217880249},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5024967193603516},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46270138025283813},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.41551411151885986},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3306643068790436},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2927147448062897},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.238111674785614},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.20317047834396362},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889473","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":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W3015591594","https://openalex.org/W4226442948","https://openalex.org/W4312933868","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4387969125","https://openalex.org/W4392902953","https://openalex.org/W4392909615","https://openalex.org/W4396877837","https://openalex.org/W4400033239","https://openalex.org/W4403780823","https://openalex.org/W4404037229","https://openalex.org/W6766673545","https://openalex.org/W6769627184","https://openalex.org/W6783867762","https://openalex.org/W6845479124","https://openalex.org/W6849109464","https://openalex.org/W6849307739","https://openalex.org/W6850625674","https://openalex.org/W6851997505","https://openalex.org/W6858268588","https://openalex.org/W6862995742"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2909726438"],"abstract_inverted_index":{"Generative":[0],"models":[1,12,114,131],"have":[2],"shown":[3],"significant":[4],"achievements":[5],"in":[6,142],"audio":[7,46,53,71,98],"generation":[8,54,113],"tasks.":[9],"However,":[10],"existing":[11],"struggle":[13],"with":[14,48,94,115],"complex":[15,122],"and":[16,33,73,103,147],"detailed":[17,64],"prompts,":[18],"leading":[19],"to":[20,42,62],"potential":[21,139],"performance":[22,120],"degradation.":[23],"We":[24,56,106],"hypothesize":[25],"that":[26,109],"this":[27],"problem":[28],"stems":[29],"from":[30],"the":[31,36,111,119,130,138],"simplicity":[32],"scarcity":[34],"of":[35,129,140],"training":[37,110],"data.":[38],"This":[39],"work":[40],"aims":[41],"create":[43],"a":[44,80],"large-scale":[45],"dataset":[47],"rich":[49],"captions":[50,65],"for":[51],"improving":[52],"models.":[55],"first":[57],"develop":[58],"an":[59],"automated":[60],"pipeline":[61],"generate":[63],"by":[66],"transforming":[67],"predicted":[68],"visual":[69],"captions,":[70,72],"tagging":[74],"labels":[75],"into":[76],"comprehensive":[77],"descriptions":[78],"using":[79],"Large":[81],"Language":[82],"Model":[83],"(LLM).":[84],"The":[85],"resulting":[86],"dataset,":[87],"Sound-VECaps,":[88],"comprises":[89],"1.66M":[90],"high-quality":[91],"audio-caption":[92],"pairs":[93],"enriched":[95],"details":[96],"including":[97],"event":[99],"orders,":[100],"occurred":[101],"places":[102],"environment":[104],"information.":[105],"then":[107],"demonstrate":[108],"text-to-audio":[112],"Sound-VECaps":[116,141],"significantly":[117],"improves":[118],"on":[121,132],"prompts.":[123],"Furthermore,":[124],"we":[125],"conduct":[126],"ablation":[127],"studies":[128],"several":[133],"downstream":[134],"audio-language":[135],"tasks,":[136],"showing":[137],"advancing":[143],"audio-text":[144],"representation":[145],"learning.Dataset":[146],"demos":[148],"are":[149],"available":[150],"at":[151],"https://yyua8222.github.io/Sound-VECaps-demo/.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}
