{"id":"https://openalex.org/W3097791920","doi":"https://doi.org/10.21437/interspeech.2020-2087","title":"A Transformer-Based Audio Captioning Model with Keyword Estimation","display_name":"A Transformer-Based Audio Captioning Model with Keyword Estimation","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097791920","doi":"https://doi.org/10.21437/interspeech.2020-2087","mag":"3097791920"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2087","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuma Koizumi","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110780218","display_name":"Kyosuke Nishida","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kyosuke Nishida","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017806490","display_name":"Masahiro Yasuda","orcid":"https://orcid.org/0000-0002-8384-8167"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahiro Yasuda","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108799515","display_name":"Shoichiro Saito","orcid":"https://orcid.org/0000-0002-8712-0464"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoichiro Saito","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101503856"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":6.737,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.9793457,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1977","last_page":"1981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9905999898910522,"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":0.9829000234603882,"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":0.9652842283248901},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8361628651618958},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7622815370559692},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6100760102272034},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5769402980804443},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5684441328048706},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5402301549911499},{"id":"https://openalex.org/keywords/indeterminacy","display_name":"Indeterminacy (philosophy)","score":0.5069237351417542},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4938707947731018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4474419057369232},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4279322028160095},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13823291659355164},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07903352379798889}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9652842283248901},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8361628651618958},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7622815370559692},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6100760102272034},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5769402980804443},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5684441328048706},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5402301549911499},{"id":"https://openalex.org/C2777366796","wikidata":"https://www.wikidata.org/wiki/Q6017758","display_name":"Indeterminacy (philosophy)","level":2,"score":0.5069237351417542},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4938707947731018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4474419057369232},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4279322028160095},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13823291659355164},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07903352379798889},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2087","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1521626219","https://openalex.org/W1522301498","https://openalex.org/W1533561824","https://openalex.org/W1902237438","https://openalex.org/W2033875152","https://openalex.org/W2103235956","https://openalex.org/W2130942839","https://openalex.org/W2408239454","https://openalex.org/W2493916176","https://openalex.org/W2526050071","https://openalex.org/W2552161745","https://openalex.org/W2556388456","https://openalex.org/W2575842049","https://openalex.org/W2593116425","https://openalex.org/W2745461083","https://openalex.org/W2803930360","https://openalex.org/W2889518897","https://openalex.org/W2916103538","https://openalex.org/W2962884827","https://openalex.org/W2963515589","https://openalex.org/W2964213897","https://openalex.org/W2981822321","https://openalex.org/W2982554818","https://openalex.org/W2982669287","https://openalex.org/W3001801466","https://openalex.org/W3013444301","https://openalex.org/W3015591594","https://openalex.org/W3015700860","https://openalex.org/W3038899388","https://openalex.org/W3049446265","https://openalex.org/W3121952123","https://openalex.org/W4289329167","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W3217195652","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":{"One":[0],"of":[1,35,66,72],"the":[2,10,17,58,63,70,93,98,103,126],"problems":[3],"with":[4,26,51,62],"automated":[5],"audio":[6,18,90],"captioning":[7],"(AAC)":[8],"is":[9],"indeterminacy":[11,60],"in":[12,31,40,92],"word":[13,86],"selection":[14],"corresponding":[15,88],"to":[16,89,102,106],"event/scene.Since":[19],"one":[20],"acoustic":[21,73],"event/scene":[22],"can":[23],"be":[24],"described":[25],"several":[27],"words,":[28],"it":[29],"results":[30,110],"a":[32,47,85,112],"combinatorial":[33],"explosion":[34],"possible":[36],"captions":[37],"and":[38,96,122,128],"difficulty":[39],"training.To":[41],"solve":[42],"this":[43],"problem,":[44],"we":[45],"propose":[46],"Transformer-based":[48],"audio-captioning":[49],"model":[50],"keyword":[52,79],"estimation":[53],"called":[54],"TRACKE.It":[55],"simultaneously":[56],"solves":[57],"word-selection":[59,108],"problem":[61],"main":[64],"task":[65],"AAC":[67,114],"while":[68,100],"executing":[69],"sub-task":[71],"event":[74],"detection/acoustic":[75],"scene":[76],"classification":[77],"(i.e.,":[78],"estimation).TRACKE":[80],"estimates":[81],"keywords,":[82],"which":[83],"comprise":[84],"set":[87],"events/scenes":[91],"input":[94],"audio,":[95],"generates":[97],"caption":[99,127],"referring":[101],"estimated":[104,124],"keywords":[105],"reduce":[107],"indeterminacy.Experimental":[109],"on":[111],"public":[113],"dataset":[115],"indicate":[116],"that":[117],"TRACKE":[118],"achieved":[119],"state-ofthe-art":[120],"performance":[121],"successfully":[123],"both":[125],"its":[129],"keywords.":[130]},"counts_by_year":[{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
