{"id":"https://openalex.org/W4415708414","doi":"https://doi.org/10.1109/icme59968.2025.11210031","title":"Diverse Audio Caption Generation with Semantic-aware Diffusion Model","display_name":"Diverse Audio Caption Generation with Semantic-aware Diffusion Model","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708414","doi":"https://doi.org/10.1109/icme59968.2025.11210031"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5101449309","display_name":"Hualei Wang","orcid":"https://orcid.org/0000-0003-3127-3362"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hualei Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108132430","display_name":"Yiming Li","orcid":"https://orcid.org/0000-0002-0688-4842"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Li","raw_affiliation_strings":["Chinese Academy of Sciences,Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410371","display_name":"Hong Liu","orcid":"https://orcid.org/0000-0003-3685-6268"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Liu","raw_affiliation_strings":["Chinese Academy of Sciences,Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115695066","display_name":"Xiangdong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangdong Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101449309"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42429014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.621399998664856,"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":0.621399998664856,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.06809999793767929,"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/T10860","display_name":"Speech and Audio Processing","score":0.06629999727010727,"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":0.8312000036239624},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.593999981880188},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4862000048160553},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4767000079154968},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.4706000089645386},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4675999879837036},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3084999918937683}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8312000036239624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950999736785889},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.593999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246000289916992},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4675999879837036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44350001215934753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3231000006198883},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3084999918937683},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2824000120162964},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.2759000062942505},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":19,"referenced_works":["https://openalex.org/W3015591594","https://openalex.org/W3034999214","https://openalex.org/W4224926581","https://openalex.org/W4312933868","https://openalex.org/W4372260310","https://openalex.org/W4372340819","https://openalex.org/W4385569744","https://openalex.org/W4385767932","https://openalex.org/W4386072307","https://openalex.org/W4389518872","https://openalex.org/W4399341722","https://openalex.org/W4399881416","https://openalex.org/W4400033239","https://openalex.org/W4401043304","https://openalex.org/W4401831361","https://openalex.org/W4403780831","https://openalex.org/W4403843325","https://openalex.org/W4408355359","https://openalex.org/W4415433595"],"related_works":[],"abstract_inverted_index":{"Audio":[0],"captioning":[1,21],"aims":[2],"to":[3,24,62,91,96,113,159],"perceive":[4],"sound":[5],"events":[6],"in":[7,38,48,57],"different":[8],"ways":[9],"and":[10,30,34,59,68,88,143,155],"describe":[11],"an":[12,124],"audio":[13,20,162],"clip":[14],"from":[15],"various":[16],"perspectives.":[17],"Most":[18],"existing":[19],"methods":[22,43],"tend":[23],"generate":[25,92],"captions":[26],"that":[27,82,128,147],"are":[28],"deterministic":[29],"simple,":[31],"lacking":[32],"diversity":[33,156],"limiting":[35],"their":[36],"applicability":[37],"real-world":[39],"scenarios.":[40],"Recently,":[41],"diffusion-based":[42],"have":[44],"achieved":[45],"significant":[46],"progress":[47],"producing":[49],"diverse":[50,161],"captions,":[51],"but":[52],"with":[53],"a":[54,78,130],"potential":[55],"compromise":[56],"accuracy":[58,154],"fluency":[60],"due":[61],"the":[63,69,101,106,110,135,141],"abstract":[64],"nature":[65],"of":[66,109],"language":[67],"variable":[70],"supervised":[71],"targets.":[72],"In":[73,94],"this":[74],"work,":[75],"we":[76,99,122],"propose":[77,123],"semantic-aware":[79],"diffusion":[80,111],"model":[81,112,149],"leverages":[83],"its":[84],"intrinsic":[85],"stochastic":[86],"sampling":[87],"global":[89,102],"context":[90],"captions.":[93],"order":[95],"maintain":[97],"accuracy,":[98],"integrate":[100],"CLAP":[103],"embeddings":[104],"into":[105],"denoising":[107,132],"process":[108,127],"serve":[114],"as":[115],"semantic":[116],"context.":[117],"To":[118],"further":[119],"enhance":[120],"diversity,":[121],"optimized":[125],"inference":[126],"incorporates":[129],"dynamic":[131],"strategy":[133],"during":[134],"token-restored":[136],"stage.":[137],"Extensive":[138],"experiments":[139],"on":[140,153],"AudioCaps":[142],"Clotho":[144],"dataset":[145],"demonstrate":[146],"our":[148],"achieves":[150],"superior":[151],"results":[152],"metrics":[157],"compared":[158],"state-of-the-art":[160],"caption":[163],"methods.":[164]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}