{"id":"https://openalex.org/W3016160783","doi":"https://doi.org/10.1109/icassp40776.2020.9053512","title":"Espnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit","display_name":"Espnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016160783","doi":"https://doi.org/10.1109/icassp40776.2020.9053512","mag":"3016160783"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053512","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053512","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Nagoya University"],"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669485","display_name":"Ryuichi Yamamoto","orcid":"https://orcid.org/0000-0003-0299-5470"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryuichi Yamamoto","raw_affiliation_strings":["LINE Corp"],"affiliations":[{"raw_affiliation_string":"LINE Corp","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082312736","display_name":"Katsuki Inoue","orcid":null},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuki Inoue","raw_affiliation_strings":["Okayama University"],"affiliations":[{"raw_affiliation_string":"Okayama University","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101948311","display_name":"Takenori Yoshimura","orcid":"https://orcid.org/0000-0003-3964-5677"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takenori Yoshimura","raw_affiliation_strings":["Nagoya University"],"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"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":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University"],"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":["Nagoya University"],"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google AI"],"affiliations":[{"raw_affiliation_string":"Google AI","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018286848","display_name":"Xu Tan","orcid":"https://orcid.org/0000-0001-6123-4378"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xu Tan","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5078778981"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":19.4534,"has_fulltext":false,"cited_by_count":175,"citation_normalized_percentile":{"value":0.99469054,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7654","last_page":"7658"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9977999925613403,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.8187669515609741},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7280322909355164},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6350173354148865},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.4949788451194763},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48225122690200806},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44070738554000854},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4240609407424927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3679613471031189},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.29159098863601685},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20395222306251526},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09387761354446411}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187669515609741},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7280322909355164},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6350173354148865},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4949788451194763},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48225122690200806},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44070738554000854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4240609407424927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3679613471031189},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.29159098863601685},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20395222306251526},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09387761354446411},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053512","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053512","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1924770834","https://openalex.org/W1990505856","https://openalex.org/W2005522781","https://openalex.org/W2102003408","https://openalex.org/W2111284386","https://openalex.org/W2152859600","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2598638573","https://openalex.org/W2749651610","https://openalex.org/W2765486990","https://openalex.org/W2766109623","https://openalex.org/W2767052532","https://openalex.org/W2794490148","https://openalex.org/W2797310469","https://openalex.org/W2883586237","https://openalex.org/W2886769154","https://openalex.org/W2890964092","https://openalex.org/W2892140764","https://openalex.org/W2899771611","https://openalex.org/W2901739041","https://openalex.org/W2938947737","https://openalex.org/W2945078028","https://openalex.org/W2946200149","https://openalex.org/W2949382160","https://openalex.org/W2952711665","https://openalex.org/W2962780374","https://openalex.org/W2963300588","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2964060510","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2969049672","https://openalex.org/W2970730223","https://openalex.org/W2972359262","https://openalex.org/W2972818416","https://openalex.org/W2972889948","https://openalex.org/W3007328579","https://openalex.org/W3015338123","https://openalex.org/W4289383906","https://openalex.org/W4298580827","https://openalex.org/W6603838645","https://openalex.org/W6623517193","https://openalex.org/W6629717138","https://openalex.org/W6631362777","https://openalex.org/W6640212811","https://openalex.org/W6651937441","https://openalex.org/W6675380101","https://openalex.org/W6677973343","https://openalex.org/W6745289305","https://openalex.org/W6748409065","https://openalex.org/W6749489859","https://openalex.org/W6750489868","https://openalex.org/W6753186555","https://openalex.org/W6754925833","https://openalex.org/W6755300632","https://openalex.org/W6756040250","https://openalex.org/W6756104738","https://openalex.org/W6762242920","https://openalex.org/W6763832098","https://openalex.org/W6767245602","https://openalex.org/W6903921188"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W3196421258","https://openalex.org/W4387301579","https://openalex.org/W2763956190","https://openalex.org/W3008587939","https://openalex.org/W4400488565","https://openalex.org/W4404782863"],"abstract_inverted_index":{"This":[0,113],"paper":[1,114],"introduces":[2],"a":[3,85,148],"new":[4],"end-to-end":[5],"text-to-speech":[6],"(E2E-TTS)":[7],"toolkit":[8,20,23,66,120,160],"named":[9],"ESPnet-TTS,":[10],"which":[11],"is":[12,161],"an":[13],"extension":[14],"of":[15,73,75,94,118,153],"the":[16,42,54,58,76,88,92,116,119,142,156],"open-source":[17],"speech":[18,45],"processing":[19],"ESPnet.":[21],"The":[22,49,65,129,159],"supports":[24],"state-of-":[25],"the-art":[26],"E2E-TTS":[27],"models,":[28],"including":[29],"Tacotron":[30],"2,":[31],"Transformer":[32],"TTS,":[33,98],"and":[34,36,71,103,110,121],"FastSpeech,":[35],"also":[37,67],"provides":[38,68],"recipes":[39,50,77],"inspired":[40],"by":[41],"Kaldi":[43],"automatic":[44],"recognition":[46],"(ASR)":[47],"toolkit.":[48],"are":[51],"based":[52],"on":[53,155],"design":[55,90,117],"unified":[56,89],"with":[57,97,107,126],"ESPnet":[59],"ASR":[60,95,109],"recipe,":[61],"providing":[62],"high":[63],"reproducibility.":[64],"pre-trained":[69],"models":[70,135],"samples":[72],"all":[74],"so":[78],"that":[79,133],"users":[80],"can":[81,136],"use":[82],"it":[83],"as":[84],"baseline.":[86],"Furthermore,":[87],"enables":[91],"integration":[93],"functions":[96],"e.g.,":[99],"ASR-based":[100],"objective":[101],"evaluation":[102,123],"semi-":[104],"supervised":[105],"learning":[106],"both":[108],"TTS":[111],"models.":[112],"describes":[115],"experimental":[122,130],"in":[124,147],"comparison":[125],"other":[127,143],"toolkits.":[128],"results":[131],"show":[132],"our":[134],"achieve":[137],"state-of-the-art":[138],"performance":[139],"comparable":[140],"to":[141],"latest":[144],"toolkits,":[145],"resulting":[146],"mean":[149],"opinion":[150],"score":[151],"(MOS)":[152],"4.25":[154],"LJSpeech":[157],"dataset.":[158],"publicly":[162],"available":[163],"at":[164],"https://github.com/espnet/espnet.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":49},{"year":2020,"cited_by_count":38}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}