{"id":"https://openalex.org/W3162517041","doi":"https://doi.org/10.1109/icassp39728.2021.9413973","title":"Non-Autoregressive Sequence-To-Sequence Voice Conversion","display_name":"Non-Autoregressive Sequence-To-Sequence Voice Conversion","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162517041","doi":"https://doi.org/10.1109/icassp39728.2021.9413973","mag":"3162517041"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/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":["TARVO Inc.,Japan","Nagoya University, Japan","TARVO Inc., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TARVO Inc.,Japan","institution_ids":[]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"TARVO Inc., Japan","institution_ids":[]}]},{"author_position":"middle","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":false,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037417355","display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0001-7801-147X"},"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":"Kazuhiro Kobayashi","raw_affiliation_strings":["TARVO Inc.,Japan","TARVO Inc., Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TARVO Inc.,Japan","institution_ids":[]},{"raw_affiliation_string":"TARVO Inc., Japan","institution_ids":[]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"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","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7068","last_page":"7072"},"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":0.995199978351593,"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":0.9945999979972839,"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/autoregressive-model","display_name":"Autoregressive model","score":0.8595203161239624},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6858124136924744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6711649894714355},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5773685574531555},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5736338496208191},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5496387481689453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3628808259963989},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15231770277023315},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.13001394271850586},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10989263653755188},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09032362699508667}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8595203161239624},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6858124136924744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6711649894714355},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5773685574531555},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5736338496208191},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5496387481689453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3628808259963989},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15231770277023315},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.13001394271850586},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10989263653755188},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09032362699508667},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"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/icassp39728.2021.9413973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W1590808459","https://openalex.org/W2052871313","https://openalex.org/W2077865492","https://openalex.org/W2120605154","https://openalex.org/W2133564696","https://openalex.org/W2142300631","https://openalex.org/W2152205330","https://openalex.org/W2294038178","https://openalex.org/W2406654659","https://openalex.org/W2471520273","https://openalex.org/W2567070169","https://openalex.org/W2767286248","https://openalex.org/W2898654681","https://openalex.org/W2899877258","https://openalex.org/W2901254300","https://openalex.org/W2945613576","https://openalex.org/W2946200149","https://openalex.org/W2962780374","https://openalex.org/W2963403868","https://openalex.org/W2963609956","https://openalex.org/W2963970792","https://openalex.org/W2964110616","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W2970730223","https://openalex.org/W2994715919","https://openalex.org/W3015338123","https://openalex.org/W3016160783","https://openalex.org/W3024476726","https://openalex.org/W3025165719","https://openalex.org/W3033411150","https://openalex.org/W3034420534","https://openalex.org/W3034729383","https://openalex.org/W3034949308","https://openalex.org/W3096567388","https://openalex.org/W3097777922","https://openalex.org/W3102905810","https://openalex.org/W3113687514","https://openalex.org/W3150572638","https://openalex.org/W4320930577","https://openalex.org/W4385245566","https://openalex.org/W6679434410","https://openalex.org/W6697024540","https://openalex.org/W6731370813","https://openalex.org/W6739901393","https://openalex.org/W6746023985","https://openalex.org/W6756102363","https://openalex.org/W6763832098","https://openalex.org/W6771070734","https://openalex.org/W6777080322","https://openalex.org/W6778823374","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W2355553914","https://openalex.org/W149862513","https://openalex.org/W2347684782","https://openalex.org/W4320472397","https://openalex.org/W2401269021","https://openalex.org/W2145654520","https://openalex.org/W4319862652","https://openalex.org/W2750037515","https://openalex.org/W2394249171","https://openalex.org/W2031981373"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3],"novel":[4],"voice":[5],"conversion":[6,120],"(VC)":[7],"method":[8],"based":[9],"on":[10],"non-autoregressive":[11],"sequence-to-sequence":[12],"(NAR-S2S)":[13],"models.":[14],"Inspired":[15],"by":[16],"the":[17,31,35,40,46,60,74,85,92,108],"great":[18],"success":[19],"of":[20,45,98,103],"NAR-S2S":[21],"models":[22,125],"such":[23,79,126],"as":[24,80,127],"FastSpeech":[25],"in":[26],"text-to-speech":[27],"(TTS),":[28],"we":[29,64],"extend":[30,65],"FastSpeech2":[32],"model":[33,110],"for":[34],"VC":[36],"problem.":[37],"We":[38],"introduce":[39],"convolution-augmented":[41],"Transformer":[42],"(Conformer)":[43],"instead":[44],"Transformer,":[47],"making":[48],"it":[49],"possible":[50],"to":[51,68,71,113],"capture":[52],"both":[53],"local":[54],"and":[55,82,100,118,129],"global":[56],"context":[57],"information":[58],"from":[59],"input":[61],"sequence.":[62],"Furthermore,":[63],"variance":[66,69],"predictors":[67],"converters":[70],"explicitly":[72],"convert":[73],"source":[75],"speaker\u2019s":[76],"prosody":[77],"components":[78],"pitch":[81],"energy":[83],"into":[84],"target":[86],"speaker.":[87],"The":[88],"experimental":[89],"evaluation":[90],"with":[91],"Japanese":[93],"speaker":[94],"dataset,":[95],"which":[96],"consists":[97],"male":[99],"female":[101],"speakers":[102],"1,000":[104],"utterances,":[105],"demonstrates":[106],"that":[107],"proposed":[109],"enables":[111],"us":[112],"perform":[114],"more":[115],"stable,":[116],"faster,":[117],"better":[119],"than":[121],"autoregressive":[122],"S2S":[123],"(AR-S2S)":[124],"Tacotron2":[128],"Transformer.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}