{"id":"https://openalex.org/W2940200615","doi":"https://doi.org/10.1109/icassp.2019.8682816","title":"Multi-speaker Sequence-to-sequence Speech Synthesis for Data Augmentation in Acoustic-to-word Speech Recognition","display_name":"Multi-speaker Sequence-to-sequence Speech Synthesis for Data Augmentation in Acoustic-to-word Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2940200615","doi":"https://doi.org/10.1109/icassp.2019.8682816","mag":"2940200615"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/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"],"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"]}]},{"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"],"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"]}]},{"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"],"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"]}]},{"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"],"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"]}]}],"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":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6161","last_page":"6165"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/T11309","display_name":"Music and Audio Processing","score":0.9939000010490417,"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/speech-recognition","display_name":"Speech recognition","score":0.7886839509010315},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7218791246414185},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7205973863601685},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5596557855606079},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5414957404136658},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42788854241371155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3777206540107727},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11746490001678467}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7886839509010315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7218791246414185},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7205973863601685},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5596557855606079},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5414957404136658},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42788854241371155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3777206540107727},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11746490001678467},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1533416326","https://openalex.org/W2095705004","https://openalex.org/W2114925438","https://openalex.org/W2127141656","https://openalex.org/W2183341477","https://openalex.org/W2327501763","https://openalex.org/W2577366047","https://openalex.org/W2597757402","https://openalex.org/W2608712415","https://openalex.org/W2619368999","https://openalex.org/W2765486990","https://openalex.org/W2798405286","https://openalex.org/W2808706139","https://openalex.org/W2888779557","https://openalex.org/W2889074736","https://openalex.org/W2889504751","https://openalex.org/W2890197052","https://openalex.org/W2892140764","https://openalex.org/W2899771611","https://openalex.org/W2912937645","https://openalex.org/W2962699523","https://openalex.org/W2962826786","https://openalex.org/W2962961016","https://openalex.org/W2963240019","https://openalex.org/W2963691546","https://openalex.org/W2963712897","https://openalex.org/W2963796886","https://openalex.org/W2963827914","https://openalex.org/W2963920996","https://openalex.org/W2964012862","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W6601563604","https://openalex.org/W6623517193","https://openalex.org/W6629052376","https://openalex.org/W6631190155","https://openalex.org/W6674330103","https://openalex.org/W6745289305","https://openalex.org/W6746700228","https://openalex.org/W6749489859","https://openalex.org/W6752888775","https://openalex.org/W6754925833","https://openalex.org/W6756040250","https://openalex.org/W6765987481"],"related_works":["https://openalex.org/W1569283511","https://openalex.org/W2216757598","https://openalex.org/W4387496629","https://openalex.org/W4236193183","https://openalex.org/W3013209356","https://openalex.org/W2053866214","https://openalex.org/W2607505004","https://openalex.org/W2112284452","https://openalex.org/W2231795205","https://openalex.org/W127416991"],"abstract_inverted_index":{"The":[0,112],"acoustic-to-word":[1],"(A2W)":[2],"automatic":[3],"speech":[4,44,62,77,101,108,114,140,146],"recognition":[5],"(ASR)":[6],"realizes":[7],"very":[8],"fast":[9],"decoding":[10],"with":[11,83,118,144,166],"a":[12,73,91,119,171],"simple":[13],"architecture":[14],"and":[15,30,50,177],"achieves":[16],"state-of-the-art":[17],"performance.":[18],"However,":[19],"the":[20,25,37,69,100,123,135,149,162,167,175,178],"A2W":[21,156,163],"model":[22,79,164,169],"suffers":[23],"from":[24,132],"out-of-vocabulary":[26],"(OOV)":[27],"word":[28],"problem":[29],"cannot":[31],"use":[32],"text-only":[33],"data":[34,67],"to":[35,54,64,89,128,152],"improve":[36],"language":[38],"modeling":[39],"capability.":[40],"Meanwhile,":[41],"sequence-to-sequence":[42,60],"neural":[43,61],"synthesis":[45,63,78],"has":[46],"also":[47],"been":[48],"developed":[49],"achieved":[51,170],"naturalness":[52],"comparable":[53],"human":[55],"speech.":[56],"We":[57],"investigate":[58],"leveraging":[59],"augment":[65],"training":[66],"for":[68],"ASR":[70,87],"system":[71],"in":[72,122],"target":[74,136],"domain.":[75,137],"While":[76],"is":[80,116],"usually":[81],"trained":[82,117,165],"single":[84,179],"speaker":[85,180],"data,":[86],"needs":[88],"cover":[90],"variety":[92],"of":[93,109,134,148],"speakers.":[94,111],"In":[95],"this":[96],"work,":[97],"we":[98],"extend":[99],"synthesizer":[102,115],"so":[103],"that":[104,161],"it":[105],"can":[106],"output":[107],"many":[110],"multi-speaker":[113,168],"large":[120],"corpus":[121],"source":[124,150],"domain,":[125],"then":[126],"used":[127],"generate":[129],"acoustic":[130],"features":[131,141,147],"texts":[133],"These":[138],"synthesized":[139],"are":[142],"combined":[143],"real":[145],"domain":[151],"train":[153],"an":[154],"attention-based":[155],"model.":[157,181],"Experimental":[158],"results":[159],"show":[160],"significant":[172],"improvement":[173],"over":[174],"baseline":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}