{"id":"https://openalex.org/W4210327373","doi":"https://doi.org/10.1109/asru51503.2021.9688218","title":"Data Augmentation for ASR Using TTS Via a Discrete Representation","display_name":"Data Augmentation for ASR Using TTS Via a Discrete Representation","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210327373","doi":"https://doi.org/10.1109/asru51503.2021.9688218"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688218","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5103835523","display_name":"Sei Ueno","orcid":"https://orcid.org/0000-0002-2255-3154"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sei Ueno","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110763152","display_name":"Shinsuke Sakai","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinsuke Sakai","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"68","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9961000084877014,"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/computer-science","display_name":"Computer science","score":0.7697029113769531},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7388134002685547},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5883004665374756},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5781676769256592},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5734605193138123},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44427043199539185},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.44186797738075256},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.43192532658576965},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4275229871273041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3759843409061432},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33445295691490173},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.26010048389434814},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11296316981315613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7697029113769531},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7388134002685547},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5883004665374756},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5781676769256592},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5734605193138123},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44427043199539185},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.44186797738075256},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.43192532658576965},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4275229871273041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3759843409061432},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33445295691490173},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.26010048389434814},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11296316981315613},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688218","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":52,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1915251500","https://openalex.org/W2251321385","https://openalex.org/W2471520273","https://openalex.org/W2577366047","https://openalex.org/W2619368999","https://openalex.org/W2739427748","https://openalex.org/W2752796333","https://openalex.org/W2883586237","https://openalex.org/W2888779557","https://openalex.org/W2903739847","https://openalex.org/W2912937645","https://openalex.org/W2936774411","https://openalex.org/W2940200615","https://openalex.org/W2962699523","https://openalex.org/W2962759037","https://openalex.org/W2962784628","https://openalex.org/W2963799213","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2972359262","https://openalex.org/W2972991710","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W3008480565","https://openalex.org/W3015280134","https://openalex.org/W3015449694","https://openalex.org/W3033411150","https://openalex.org/W3095687973","https://openalex.org/W3097632072","https://openalex.org/W3097777922","https://openalex.org/W3097890746","https://openalex.org/W3161296985","https://openalex.org/W3162037819","https://openalex.org/W3162244132","https://openalex.org/W3198836239","https://openalex.org/W6629717138","https://openalex.org/W6640059789","https://openalex.org/W6691770337","https://openalex.org/W6741328424","https://openalex.org/W6741807409","https://openalex.org/W6758673196","https://openalex.org/W6761176036","https://openalex.org/W6761335673","https://openalex.org/W6765987481","https://openalex.org/W6767111847","https://openalex.org/W6769196770","https://openalex.org/W6778823374","https://openalex.org/W6784492714","https://openalex.org/W6785674339","https://openalex.org/W6796162119","https://openalex.org/W7027429494"],"related_works":["https://openalex.org/W1809875158","https://openalex.org/W1658560081","https://openalex.org/W2588431733","https://openalex.org/W2342410338","https://openalex.org/W2102737569","https://openalex.org/W106163518","https://openalex.org/W87187291","https://openalex.org/W2571805528","https://openalex.org/W321122172","https://openalex.org/W4210327373"],"abstract_inverted_index":{"While":[0],"end-to-end":[1],"automatic":[2],"speech":[3,17,42,51,76,90],"recognition":[4],"(ASR)":[5],"has":[6,57],"achieved":[7],"high":[8],"performance,":[9],"it":[10,56,159],"requires":[11],"a":[12,36,70,83,88,120],"huge":[13],"amount":[14],"of":[15,100,119],"paired":[16],"and":[18,47,103,163],"transcription":[19],"data":[20,24,43,46,53,84,149],"for":[21,52],"training.":[22],"Recently,":[23],"augmentation":[25,85,150],"methods":[26],"have":[27,69],"actively":[28],"been":[29,58],"investigated.":[30],"One":[31],"method":[32,86,146,151],"is":[33],"to":[34,40,171],"use":[35,48,118],"text-to-speech":[37],"(TTS)":[38],"system":[39],"gen-erate":[41],"from":[44],"text-only":[45],"the":[49,61,74,104,108,117,135,144,148,153,164,172],"generated":[50,165],"augmentation,":[54],"but":[55,132],"found":[59,157],"that":[60,116,143,158],"synthesized":[62],"log":[63],"Mel-scale":[64],"filterbank":[65],"(lmfb)":[66],"features":[67,166],"could":[68],"serious":[71],"mismatch":[72,136],"with":[73,137],"real":[75,138,173],"features.":[77],"In":[78],"this":[79],"study,":[80],"we":[81],"propose":[82],"via":[87],"discrete":[89,96,121],"representation.":[91],"The":[92],"TTS":[93,129],"model":[94],"predicts":[95],"ID":[97,109],"sequences":[98,110],"instead":[99],"lmfb":[101],"features,":[102],"ASR":[105],"also":[106,133],"uses":[107],"as":[111],"training":[112,130],"data.":[113,139],"We":[114,156],"expect":[115],"representation":[122],"based":[123],"on":[124],"vq-wav2vec":[125],"not":[126],"only":[127],"makes":[128],"easier":[131],"mitigates":[134],"Experimental":[140],"evaluations":[141],"show":[142],"pro-posed":[145],"outperforms":[147],"using":[152],"conventional":[154],"TTS.":[155],"reduces":[160],"speaker":[161],"dependency,":[162],"are":[167],"distributed":[168],"more":[169],"closely":[170],"ones.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}