{"id":"https://openalex.org/W2972544500","doi":"https://doi.org/10.21437/interspeech.2019-2307","title":"Non-Parallel Voice Conversion with Cyclic Variational Autoencoder","display_name":"Non-Parallel Voice Conversion with Cyclic Variational Autoencoder","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972544500","doi":"https://doi.org/10.21437/interspeech.2019-2307","mag":"2972544500"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2307","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5050897938","display_name":"Patrick Lumban Tobing","orcid":"https://orcid.org/0000-0003-2792-8418"},"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":"Patrick Lumban Tobing","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, 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":["Graduate School of Information Science, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, 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":["Graduate School of Information Science, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, 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":["Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, 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":["Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, 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":67,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"674","last_page":"678"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9950000047683716,"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":0.9950000047683716,"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":0.9911999702453613,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9818999767303467,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/autoencoder","display_name":"Autoencoder","score":0.8799885511398315},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5942240953445435},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4260393977165222},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41965818405151367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23603489995002747},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12041172385215759}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8799885511398315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5942240953445435},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4260393977165222},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41965818405151367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23603489995002747},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12041172385215759}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-2307","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4000000059604645,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1628655565","display_name":null,"funder_award_id":"JPMJPR1657","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"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/G6616750388","display_name":null,"funder_award_id":"JP17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1959608418","https://openalex.org/W2032130465","https://openalex.org/W2056852181","https://openalex.org/W2067175291","https://openalex.org/W2078435788","https://openalex.org/W2095705004","https://openalex.org/W2120605154","https://openalex.org/W2142300631","https://openalex.org/W2148846882","https://openalex.org/W2156142001","https://openalex.org/W2157331557","https://openalex.org/W2161476805","https://openalex.org/W2161727827","https://openalex.org/W2169579015","https://openalex.org/W2187234408","https://openalex.org/W2471520273","https://openalex.org/W2475998840","https://openalex.org/W2519091744","https://openalex.org/W2532494225","https://openalex.org/W2651834199","https://openalex.org/W2758785877","https://openalex.org/W2770751809","https://openalex.org/W2794725088","https://openalex.org/W2804998325","https://openalex.org/W2805669069","https://openalex.org/W2887264325","https://openalex.org/W2936002583","https://openalex.org/W2962850167","https://openalex.org/W2962896155","https://openalex.org/W2963035245","https://openalex.org/W2963799213","https://openalex.org/W2964069186","https://openalex.org/W2964700958","https://openalex.org/W3125709657"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2752972570","https://openalex.org/W4297051394","https://openalex.org/W2734887215","https://openalex.org/W2803255133"],"abstract_inverted_index":{"In":[0],"this":[1,100,104],"paper,":[2],"we":[3,106],"present":[4],"a":[5,9,24,29,34,41,46,56,97],"novel":[6],"technique":[7],"for":[8,152],"non-parallel":[10,80],"voice":[11],"conversion":[12,117,186],"(VC)":[13],"with":[14,33,59,66,176],"the":[15,49,68,79,83,94,116,121,126,146,153,159,162,183,189],"use":[16,109],"of":[17,43,96,161,170,188],"cyclic":[18,131,139,147],"variational":[19,25],"autoencoder":[20,26],"(CycleVAE)-based":[21],"spectral":[22,111],"modeling.In":[23],"(VAE)":[27],"framework,":[28],"latent":[30,51,174],"space,":[31],"usually":[32],"Gaussian":[35],"prior,":[36],"is":[37],"used":[38],"to":[39,62,78,102,108,128],"encode":[40],"set":[42],"input":[44,151],"features.In":[45],"VAE-based":[47],"VC,":[48,165],"encoded":[50],"features":[52,123,149,175],"are":[53],"fed":[54],"into":[55,125],"decoder,":[57],"along":[58],"speaker-coding":[60],"features,":[61],"generate":[63],"estimated":[64],"spectra":[65,85,133],"either":[67],"original":[69],"speaker":[70,75],"identity":[71,76],"(reconstructed)":[72],"or":[73],"another":[74],"(converted).Due":[77],"modeling":[81],"condition,":[82],"converted":[84,122,171,190],"can":[86,135,141],"not":[87],"be":[88,136,142],"directly":[89,137],"optimized,":[90],"which":[91,166],"heavily":[92],"degrades":[93],"performance":[95],"VAEbased":[98],"VC.In":[99],"work,":[101],"overcome":[103],"problem,":[105],"propose":[107],"CycleVAE-based":[110,164],"model":[112],"that":[113,134],"indirectly":[114],"optimizes":[115],"flow":[118,140],"by":[119,144],"recycling":[120],"back":[124],"system":[127],"obtain":[129],"corresponding":[130],"reconstructed":[132,148],"optimized.The":[138],"continued":[143],"using":[145],"as":[150],"next":[154],"cycle.The":[155],"experimental":[156],"results":[157],"demonstrate":[158],"effectiveness":[160],"proposed":[163],"yields":[167],"higher":[168,177],"accuracy":[169,187],"spectra,":[172],"generates":[173],"correlation":[178],"degree,":[179],"and":[180,185],"significantly":[181],"improves":[182],"quality":[184],"speech.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":19}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}