{"id":"https://openalex.org/W3205708381","doi":"https://doi.org/10.1109/icassp43922.2022.9746894","title":"Diverse Audio Captioning Via Adversarial Training","display_name":"Diverse Audio Captioning Via Adversarial Training","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3205708381","doi":"https://doi.org/10.1109/icassp43922.2022.9746894","mag":"3205708381"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746894","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5070892237","display_name":"Xinhao Mei","orcid":"https://orcid.org/0000-0001-6079-5130"},"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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xinhao Mei","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080214850","display_name":"Xubo Liu","orcid":"https://orcid.org/0000-0002-2558-0959"},"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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000386328","display_name":"Jianyuan Sun","orcid":"https://orcid.org/0000-0001-8605-8825"},"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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianyuan Sun","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8882","last_page":"8886"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9230390787124634},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8209692239761353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5381228923797607},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4667993187904358},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46106016635894775},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.44671037793159485},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4437284767627716},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1353849470615387}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9230390787124634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8209692239761353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5381228923797607},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4667993187904358},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46106016635894775},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.44671037793159485},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4437284767627716},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1353849470615387},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746894","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11160960370002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8857457899","display_name":null,"funder_award_id":"EP/T019751/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320025","display_name":"British Council","ror":"https://ror.org/00t3pr326"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"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":38,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1924770834","https://openalex.org/W1956340063","https://openalex.org/W2099471712","https://openalex.org/W2101105183","https://openalex.org/W2154652894","https://openalex.org/W2155027007","https://openalex.org/W2506483933","https://openalex.org/W2604178507","https://openalex.org/W2795601629","https://openalex.org/W2945761034","https://openalex.org/W2962968835","https://openalex.org/W2963084599","https://openalex.org/W2964213897","https://openalex.org/W2964268978","https://openalex.org/W3015591594","https://openalex.org/W3094550259","https://openalex.org/W3097791920","https://openalex.org/W3112467147","https://openalex.org/W3132747082","https://openalex.org/W3160577380","https://openalex.org/W3185739472","https://openalex.org/W3186781156","https://openalex.org/W3189036352","https://openalex.org/W4320013936","https://openalex.org/W6621543089","https://openalex.org/W6640212811","https://openalex.org/W6682631176","https://openalex.org/W6683204974","https://openalex.org/W6725318829","https://openalex.org/W6750238580","https://openalex.org/W6769635231","https://openalex.org/W6787564935","https://openalex.org/W6790805238","https://openalex.org/W6798955355","https://openalex.org/W6799303324","https://openalex.org/W6799494382","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2029561777","https://openalex.org/W1554502231","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W172797710","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562"],"abstract_inverted_index":{"Audio":[0],"captioning":[1,14,64,96],"aims":[2,106],"at":[3,107],"generating":[4],"natural":[5],"language":[6],"descriptions":[7],"for":[8,74,94],"audio":[9,13,49,63,77,82,95],"clips":[10],"automatically.":[11],"Existing":[12],"models":[15,25],"have":[16,67],"shown":[17],"promising":[18],"improvement":[19],"in":[20,122],"recent":[21],"years.":[22],"However,":[23],"these":[24],"are":[26],"mostly":[27],"trained":[28],"via":[29],"maximum":[30],"likelihood":[31],"estimation":[32],"(MLE),":[33],"which":[34,105],"tends":[35],"to":[36,70,152,156,173],"make":[37],"captions":[38,73],"generic,":[39],"simple":[40],"and":[41,57,79,111,133],"deterministic.":[42],"As":[43],"different":[44,52],"people":[45],"may":[46],"describe":[47],"an":[48,62,90],"clip":[50,78],"from":[51],"aspects":[53],"using":[54],"distinct":[55],"words":[56],"grammars,":[58],"we":[59,88],"argue":[60],"that":[61,162],"system":[65],"should":[66],"the":[68,109,134,154,157],"ability":[69],"generate":[71,167],"diverse":[72,169],"a":[75,99,123,126,146],"fixed":[76],"across":[80],"similar":[81],"clips.":[83],"To":[84,140],"address":[85,141],"this":[86,142],"problem,":[87],"propose":[89],"adversarial":[91,102],"training":[92],"framework":[93],"based":[97],"on":[98],"conditional":[100],"generative":[101],"network":[103],"(C-GAN),":[104],"improving":[108],"naturalness":[110],"diversity":[112],"of":[113,119,130],"generated":[114],"captions.":[115],"Unlike":[116],"processing":[117],"data":[118],"continuous":[120],"values":[121],"classical":[124],"GAN,":[125],"sentence":[127],"is":[128,138,150],"composed":[129],"discrete":[131,135],"tokens":[132],"sampling":[136],"process":[137],"non-differentiable.":[139],"issue,":[143],"policy":[144],"gradient,":[145],"reinforcement":[147],"learning":[148],"technique,":[149],"used":[151],"back-propagate":[153],"reward":[155],"generator.":[158],"The":[159],"results":[160],"show":[161],"our":[163],"proposed":[164],"model":[165],"can":[166],"more":[168],"captions,":[170],"as":[171],"compared":[172],"state-of-the-art":[174],"methods.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}