{"id":"https://openalex.org/W4400033239","doi":"https://doi.org/10.1109/taslp.2024.3419446","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","display_name":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400033239","doi":"https://doi.org/10.1109/taslp.2024.3419446"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3419446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3419446","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":true,"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/A5069433018","display_name":"Chutong Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chutong Meng","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0009-0001-7591-4793","affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089924305","display_name":"Haohe Liu","orcid":"https://orcid.org/0000-0003-1036-7888"},"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":"Haohe Liu","raw_affiliation_strings":["Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0003-1036-7888","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/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Ko","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017907143","display_name":"Chengqi Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengqi Zhao","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"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":"middle","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9999-6140","affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"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":4,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5070892237"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":38.8794,"has_fulltext":false,"cited_by_count":123,"citation_normalized_percentile":{"value":0.9985823,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"3339","last_page":"3354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9787999987602234,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9725000262260437,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7431439757347107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6441007256507874},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4405534267425537},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4314866364002228},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43095216155052185},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.36067110300064087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2543542981147766},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.22017011046409607},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.17403146624565125},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.07375353574752808},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06212359666824341}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7431439757347107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6441007256507874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4405534267425537},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4314866364002228},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43095216155052185},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.36067110300064087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2543542981147766},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.22017011046409607},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.17403146624565125},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.07375353574752808},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06212359666824341},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3419446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3419446","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/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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":106,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1507711477","https://openalex.org/W1522301498","https://openalex.org/W1889081078","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2033875152","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2101105183","https://openalex.org/W2103235956","https://openalex.org/W2108598243","https://openalex.org/W2185175083","https://openalex.org/W2506483933","https://openalex.org/W2561826558","https://openalex.org/W2593116425","https://openalex.org/W2746791238","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2904565150","https://openalex.org/W2916103538","https://openalex.org/W2919115771","https://openalex.org/W2949376505","https://openalex.org/W2949413565","https://openalex.org/W2964891022","https://openalex.org/W2966683369","https://openalex.org/W2982554818","https://openalex.org/W2997591391","https://openalex.org/W3001555892","https://openalex.org/W3015371781","https://openalex.org/W3015591594","https://openalex.org/W3034999214","https://openalex.org/W3044495139","https://openalex.org/W3091588028","https://openalex.org/W3094550259","https://openalex.org/W3097791920","https://openalex.org/W3103022576","https://openalex.org/W3104279398","https://openalex.org/W3104866538","https://openalex.org/W3123416659","https://openalex.org/W3162999565","https://openalex.org/W3176445421","https://openalex.org/W3176641147","https://openalex.org/W3178592608","https://openalex.org/W3193171560","https://openalex.org/W3196974791","https://openalex.org/W3197827948","https://openalex.org/W3204267711","https://openalex.org/W4205689591","https://openalex.org/W4210913346","https://openalex.org/W4221157007","https://openalex.org/W4224035735","https://openalex.org/W4224871700","https://openalex.org/W4224924125","https://openalex.org/W4226442948","https://openalex.org/W4280567182","https://openalex.org/W4284898017","https://openalex.org/W4288089799","https://openalex.org/W4312095907","https://openalex.org/W4312898271","https://openalex.org/W4312933868","https://openalex.org/W4313014461","https://openalex.org/W4313190371","https://openalex.org/W4318351475","https://openalex.org/W4367359628","https://openalex.org/W4372260310","https://openalex.org/W4372260330","https://openalex.org/W4372266552","https://openalex.org/W4372340819","https://openalex.org/W4378501696","https://openalex.org/W4385245566","https://openalex.org/W4385822467","https://openalex.org/W4385822505","https://openalex.org/W4387323811","https://openalex.org/W4387969125","https://openalex.org/W4387969422","https://openalex.org/W4389325660","https://openalex.org/W4396877837","https://openalex.org/W4403780823","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6769627184","https://openalex.org/W6773248631","https://openalex.org/W6779823529","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6798955355","https://openalex.org/W6802577842","https://openalex.org/W6809885388","https://openalex.org/W6809964838","https://openalex.org/W6810405975","https://openalex.org/W6811013733","https://openalex.org/W6811156277","https://openalex.org/W6845479124","https://openalex.org/W6848208918","https://openalex.org/W6849105126","https://openalex.org/W6849109464","https://openalex.org/W6853249747","https://openalex.org/W6853505628","https://openalex.org/W6855932524","https://openalex.org/W6856434366","https://openalex.org/W6857054612","https://openalex.org/W6859105044"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W4390482300"],"abstract_inverted_index":{"The":[0,152],"advancement":[1],"of":[2,18,136,139,187],"audio-language":[3,20,148,180],"(AL)":[4],"multimodal":[5,149,181],"learning":[6,150,182],"tasks":[7,92],"has":[8],"been":[9],"significant":[10,164],"in":[11,91,179],"recent":[12],"years,":[13],"yet":[14],"the":[15,28,45,79,137,170,185],"limited":[16],"size":[17],"existing":[19],"datasets":[21],"poses":[22],"challenges":[23],"for":[24,88,108,169],"researchers":[25],"due":[26],"to":[27,124,176,193],"costly":[29],"and":[30,65,72,86,112,126,142,183],"time-consuming":[31],"collection":[32],"process.":[33],"To":[34,98],"address":[35],"this":[36,100],"data":[37,111],"scarcity":[38],"issue,":[39,101],"we":[40,102,173],"introduce":[41],"<italic":[42],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[43],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">WavCaps</i>,":[44],"first":[46],"large-scale":[47],"weakly-labelled":[48],"audio":[49,56,63,96],"captioning":[50],"dataset,":[51],"comprising":[52],"approximately":[53],"400":[54],"k":[55],"clips":[57,64],"with":[58],"paired":[59],"captions.":[60],"We":[61,131],"sourced":[62],"their":[66],"raw":[67,81,128],"descriptions":[68,82,129],"from":[69],"web":[70],"sources":[71],"a":[73,104,118,133,163],"sound":[74],"event":[75],"detection":[76],"dataset.":[77],"However,":[78],"online-harvested":[80],"are":[83],"highly":[84],"noisy":[85,110],"unsuitable":[87],"direct":[89],"use":[90],"such":[93],"as":[94],"automated":[95],"captioning.":[97],"overcome":[99],"propose":[103],"three-stage":[105],"processing":[106],"pipeline":[107],"filtering":[109],"generating":[113],"high-quality":[114],"captions,":[115],"where":[116],"ChatGPT,":[117],"large":[119,189],"language":[120,190],"model,":[121],"is":[122,168],"leveraged":[123],"filter":[125],"transform":[127],"automatically.":[130],"conduct":[132],"comprehensive":[134],"analysis":[135],"characteristics":[138],"WavCaps":[140,156,171],"dataset":[141,172],"evaluate":[143],"it":[144],"on":[145,155],"multiple":[146],"downstream":[147],"tasks.":[151],"systems":[153],"trained":[154],"outperform":[157],"previous":[158],"state-of-the-art":[159],"(SOTA)":[160],"models":[161,191],"by":[162],"margin.":[165],"Our":[166],"aspiration":[167],"have":[174],"proposed":[175],"facilitate":[177],"research":[178],"demonstrate":[184],"potential":[186],"utilizing":[188],"(LLMs)":[192],"enhance":[194],"academic":[195],"research.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":60},{"year":2024,"cited_by_count":41},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2024-06-27T00:00:00"}