{"id":"https://openalex.org/W3096567388","doi":"https://doi.org/10.21437/interspeech.2020-1066","title":"Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining","display_name":"Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096567388","doi":"https://doi.org/10.21437/interspeech.2020-1066","mag":"3096567388"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1066","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1066","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/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"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":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","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":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037001032","display_name":"Yi-Chiao Wu","orcid":"https://orcid.org/0000-0003-4390-1354"},"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":"Yi-Chiao Wu","raw_affiliation_strings":["Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"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":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Communication Science Laboratories, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","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, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000377034"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4676","last_page":"4680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9763000011444092,"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":0.9685999751091003,"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/transformer","display_name":"Transformer","score":0.750415563583374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.649216890335083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6357201337814331},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4542241394519806},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42964601516723633},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1705119013786316},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.13118994235992432},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12372758984565735}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.750415563583374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.649216890335083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6357201337814331},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4542241394519806},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42964601516723633},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1705119013786316},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13118994235992432},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12372758984565735},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1066","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1066","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":[{"display_name":"Peace, Justice and strong institutions","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3497787681","display_name":null,"funder_award_id":"JPMJPR1657","funder_id":"https://openalex.org/F4320338111","funder_display_name":"Precursory Research for Embryonic Science and Technology"},{"id":"https://openalex.org/G7789893098","display_name":null,"funder_award_id":"JP-MJCR19A3","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W1494198834","https://openalex.org/W1902237438","https://openalex.org/W2049686551","https://openalex.org/W2120605154","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2156142001","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2613904329","https://openalex.org/W2749651610","https://openalex.org/W2767052532","https://openalex.org/W2786868129","https://openalex.org/W2788357188","https://openalex.org/W2808706139","https://openalex.org/W2889329491","https://openalex.org/W2892009249","https://openalex.org/W2892620417","https://openalex.org/W2898654681","https://openalex.org/W2901254300","https://openalex.org/W2901607128","https://openalex.org/W2903739847","https://openalex.org/W2959758584","https://openalex.org/W2962780374","https://openalex.org/W2963609956","https://openalex.org/W2963808252","https://openalex.org/W2964243274","https://openalex.org/W2972818416","https://openalex.org/W2972970915","https://openalex.org/W2972999331","https://openalex.org/W2973142754","https://openalex.org/W2978099976","https://openalex.org/W3006777338","https://openalex.org/W3015338123","https://openalex.org/W3016160783","https://openalex.org/W3099078140","https://openalex.org/W4289299319","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,89,134],"novel":[3],"sequence-to-sequence":[4],"(seq2seq)":[5],"voice":[6],"conversion":[7],"(VC)":[8],"model":[9,115,147],"based":[10,32],"on":[11,33],"the":[12,49,52,74],"Transformer":[13,53],"architecture":[14],"with":[15,112],"text-to-speech":[16],"(TTS)":[17],"pretraining.Seq2seq":[18],"VC":[19,146],"models":[20,31,81,110],"are":[21,117],"attractive":[22],"owing":[23],"to":[24,27,47,95,119],"their":[25,70],"ability":[26],"convert":[28],"prosody.While":[29],"seq2seq":[30,80,145],"recurrent":[34],"neural":[35,40],"networks":[36,41],"(RNNs)":[37],"and":[38,73,141,153],"convolutional":[39],"(CNNs)":[42],"have":[43],"been":[44,68],"successfully":[45],"applied":[46],"VC,":[48],"use":[50],"of":[51,76,150],"network,":[54],"which":[55,102],"has":[56,65],"shown":[57],"promising":[58],"results":[59,130],"in":[60,148],"various":[61],"speech":[62,78],"processing":[63],"tasks,":[64],"not":[66],"yet":[67,91],"investigated.Nonetheless,":[69],"data-hungry":[71],"property":[72],"mispronunciation":[75],"converted":[77,128],"make":[79],"far":[82],"from":[83,98,104],"practical.To":[84],"this":[85],"end,":[86],"we":[87],"propose":[88],"simple":[90],"effective":[92,121],"pretraining":[93,135],"technique":[94],"transfer":[96],"knowledge":[97],"learned":[99],"TTS":[100,108],"models,":[101],"benefit":[103],"large-scale,":[105],"easily":[106],"accessible":[107],"corpora.VC":[109],"initialized":[111],"such":[113,133],"pretrained":[114],"parameters":[116],"able":[118],"generate":[120],"hidden":[122],"representations":[123],"for":[124],"high-fidelity,":[125],"highly":[126],"intelligible":[127],"speech.Experimental":[129],"show":[131],"that":[132],"scheme":[136],"can":[137],"facilitate":[138],"data-efficient":[139],"training":[140],"outperform":[142],"an":[143],"RNN-based":[144],"terms":[149],"intelligibility,":[151],"naturalness,":[152],"similarity.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}