{"id":"https://openalex.org/W4399881416","doi":"https://doi.org/10.1109/taslp.2024.3416686","title":"Towards Generating Diverse Audio Captions via Adversarial Training","display_name":"Towards Generating Diverse Audio Captions via Adversarial Training","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399881416","doi":"https://doi.org/10.1109/taslp.2024.3416686"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3416686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3416686","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","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/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":["Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0001-6079-5130","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0009-0004-9950-2672","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101153327","display_name":"Jianyuan Sun","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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianyuan Sun","raw_affiliation_strings":["Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K","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":["Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0002-9708-1075","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K","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":["Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8393-5703","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K","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":0.5631,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60740782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"32","issue":null,"first_page":"3311","last_page":"3323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9937000274658203,"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/T10860","display_name":"Speech and Audio Processing","score":0.9824000000953674,"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":0.8529295921325684},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8515584468841553},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5621353983879089},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.55915766954422},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5229976177215576},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5192932486534119},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4875034987926483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47939634323120117},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.47810500860214233},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09634429216384888}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8529295921325684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8515584468841553},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5621353983879089},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.55915766954422},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5229976177215576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5192932486534119},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4875034987926483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47939634323120117},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.47810500860214233},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09634429216384888},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3416686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3416686","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7697158467","display_name":"AI for Sound","funder_award_id":"EP/T019751/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"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/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":42,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133512280","https://openalex.org/W2506483933","https://openalex.org/W2593116425","https://openalex.org/W2604178507","https://openalex.org/W2739107216","https://openalex.org/W2896348597","https://openalex.org/W2919115771","https://openalex.org/W2936774411","https://openalex.org/W2962968835","https://openalex.org/W2963084599","https://openalex.org/W2964213897","https://openalex.org/W2964268978","https://openalex.org/W2964891022","https://openalex.org/W2982669287","https://openalex.org/W3015591594","https://openalex.org/W3049446265","https://openalex.org/W3094550259","https://openalex.org/W3097791920","https://openalex.org/W3123416659","https://openalex.org/W3135656708","https://openalex.org/W3160577380","https://openalex.org/W3205708381","https://openalex.org/W3205860970","https://openalex.org/W4206047378","https://openalex.org/W4221153784","https://openalex.org/W4280567182","https://openalex.org/W4297841258","https://openalex.org/W4312898271","https://openalex.org/W4385245566","https://openalex.org/W6640212811","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6683204974","https://openalex.org/W6750238580","https://openalex.org/W6779820445","https://openalex.org/W6798955355","https://openalex.org/W6799303324","https://openalex.org/W6799494382","https://openalex.org/W6802577842"],"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/W3176926761"],"abstract_inverted_index":{"Automated":[0],"audio":[1,13,46,63,82,94,108,123,138,143,166],"captioning":[2,124,167,190],"is":[3],"a":[4,57,61,136,156],"cross-modal":[5],"translation":[6],"task":[7,20],"for":[8,60,80,135],"describing":[9],"the":[10,43,77,90,128,182,197,201,217],"content":[11,44,91],"of":[12,45,92,165],"clips":[14],"with":[15,230],"natural":[16],"language":[17],"sentences.":[18],"This":[19],"has":[21,28],"attracted":[22],"increasing":[23],"attention":[24],"and":[25,70,73,105,117,172,177,196,211],"substantial":[26],"progress":[27],"been":[29],"made":[30],"in":[31],"recent":[32],"years.":[33],"Captions":[34],"generated":[35,202],"by":[36],"existing":[37],"models":[38],"are":[39,52,86,178],"generally":[40],"faithful":[41],"to":[42,88,99,130,162,193,235],"clips,":[47],"however,":[48],"these":[49],"machine-generated":[50],"captions":[51,203,229],"often":[53],"deterministic":[54],"(e.g.,":[55,66,75],"generating":[56,76],"fixed":[58,137],"caption":[59,79,170,183],"given":[62],"clip),":[64],"simple":[65,71],"using":[67,114],"common":[68],"words":[69,116],"grammar),":[72],"generic":[74],"same":[78],"similar":[81,142],"clips).":[83],"When":[84],"people":[85,97],"asked":[87],"describe":[89,106],"an":[93,107,122,150],"clip,":[95,139],"different":[96,102,205],"tend":[98],"focus":[100],"on":[101,155,216],"sound":[103],"events":[104],"clip":[109],"diversely":[110],"from":[111,204],"various":[112],"aspects":[113],"distinct":[115],"grammar.":[118],"We":[119,213],"believe":[120],"that":[121,223],"system":[125],"should":[126],"have":[127],"ability":[129],"generate":[131,194,228],"diverse":[132],"captions,":[133,195],"either":[134],"or":[140],"across":[141],"clips.":[144],"To":[145],"this":[146],"end,":[147],"we":[148],"propose":[149],"adversarial":[151,159],"training":[152],"framework":[153],"based":[154],"conditional":[157],"generative":[158],"network":[160],"(C-GAN)":[161],"improve":[163],"diversity":[164,232],"systems.":[168],"A":[169],"generator":[171,184],"two":[173],"hybrid":[174,198],"discriminators":[175,199],"compete":[176],"learned":[179],"jointly,":[180],"where":[181],"can":[185,227],"be":[186],"any":[187],"standard":[188],"encoder-decoder":[189],"model":[191,226],"used":[192],"assess":[200],"criteria,":[206],"such":[207],"as":[208,233],"their":[209],"naturalness":[210],"semantics.":[212],"conduct":[214],"experiments":[215],"Clotho":[218],"dataset.":[219],"The":[220],"results":[221],"show":[222],"our":[224],"proposed":[225],"better":[231],"compared":[234],"state-of-the-art":[236],"methods.":[237]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}