{"id":"https://openalex.org/W4224612669","doi":"https://doi.org/10.21437/interspeech.2022-10294","title":"JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech","display_name":"JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4224612669","doi":"https://doi.org/10.21437/interspeech.2022-10294"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10294","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10294","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5103786271","display_name":"Dan Lim","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dan Lim","raw_affiliation_strings":["Kakao Enterprise Corporation, Seongnam, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Kakao Enterprise Corporation, Seongnam, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074516629","display_name":"Sung\u2010Hee Jung","orcid":"https://orcid.org/0000-0002-8042-457X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunghee Jung","raw_affiliation_strings":["Kakao Enterprise Corporation, Seongnam, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Kakao Enterprise Corporation, Seongnam, Republic of Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007051105","display_name":"Eesung Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eesung Kim","raw_affiliation_strings":["Kakao Enterprise Corporation, Seongnam, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Kakao Enterprise Corporation, Seongnam, Republic of Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103786271"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2773,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.95500795,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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":0.9976999759674072,"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/T10028","display_name":"Topic Modeling","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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9919999837875366,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.7207853198051453},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6902261972427368},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4987621307373047},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40213531255722046},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.3222605586051941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3127325177192688}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7207853198051453},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6902261972427368},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4987621307373047},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40213531255722046},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3222605586051941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3127325177192688},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10294","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10294","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2593414223","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W3015338123","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3096442195","https://openalex.org/W3097538987","https://openalex.org/W3097777922","https://openalex.org/W3150572638","https://openalex.org/W3161782335","https://openalex.org/W3166714886","https://openalex.org/W3194000401","https://openalex.org/W3196001064","https://openalex.org/W3197273793","https://openalex.org/W3206375275","https://openalex.org/W4287121924","https://openalex.org/W4287761884","https://openalex.org/W4298580827","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2368779261","https://openalex.org/W2778699561","https://openalex.org/W2971982237","https://openalex.org/W2938947737","https://openalex.org/W2312526371","https://openalex.org/W2954695182","https://openalex.org/W3135486970","https://openalex.org/W4224917401","https://openalex.org/W4303519918","https://openalex.org/W2600628583"],"abstract_inverted_index":{"In":[0],"neural":[1,50],"text-to-speech":[2,78],"(TTS),":[3],"two-stage":[4],"system":[5],"or":[6],"a":[7,28,34,38,49,63,83,89],"cascade":[8,90],"of":[9,91,156],"separately":[10,92],"learned":[11,93],"models":[12],"have":[13],"shown":[14],"synthesis":[15],"quality":[16],"close":[17],"to":[18,27],"human":[19],"speech.For":[20],"example,":[21],"FastSpeech2":[22,101],"transforms":[23],"an":[24,44,66,105,127,134],"input":[25],"text":[26],"mel-spectrogram":[29],"and":[30,48,65,87,102,116,162],"then":[31],"HiFi-GAN":[32,103],"generates":[33],"raw":[35],"waveform":[36],"from":[37],"mel-spectogram":[39],"where":[40],"they":[41],"are":[42],"called":[43],"acoustic":[45,111],"feature":[46,112],"generator":[47],"vocoder":[51],"respectively.However,":[52],"their":[53],"training":[54,85,115,141],"pipeline":[55,86],"is":[56,98,109],"somewhat":[57],"cumbersome":[58],"in":[59,138],"that":[60,147],"it":[61,118],"requires":[62,121],"fine-tuning":[64],"accurate":[67],"speech-text":[68,129],"alignment":[69,106,130,135],"for":[70],"optimal":[71],"performance.In":[72],"this":[73],"work,":[74],"we":[75,123],"present":[76],"endto-end":[77],"(E2E-TTS)":[79],"model":[80,97,150],"which":[81],"has":[82],"simplified":[84],"outperforms":[88,151],"models.Specifically,":[94],"our":[95,139],"proposed":[96,149],"jointly":[99],"trained":[100],"with":[104],"module.Since":[107],"there":[108],"no":[110],"mismatch":[113],"between":[114],"inference,":[117],"does":[119],"not":[120],"fine-tuning.Furthermore,":[122],"remove":[124],"dependency":[125],"on":[126,143,158],"external":[128],"tool":[131],"by":[132],"adopting":[133],"learning":[136],"objective":[137,164],"joint":[140],"framework.Experiments":[142],"LJSpeech":[144],"corpus":[145],"shows":[146],"the":[148],"publicly":[152],"available,":[153],"stateof-the-art":[154],"implementations":[155],"ESPNet2-TTS":[157],"subjective":[159],"evaluation":[160],"(MOS)":[161],"some":[163],"evaluations.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-20T07:46:08.049788","created_date":"2025-10-10T00:00:00"}