{"id":"https://openalex.org/W3011028252","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023264","title":"Non-parallel Voice Conversion with Controllable Speaker Individuality using Variational Autoencoder","display_name":"Non-parallel Voice Conversion with Controllable Speaker Individuality using Variational Autoencoder","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011028252","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023264","mag":"3011028252"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5083304186","display_name":"Tuan Vu Ho","orcid":"https://orcid.org/0000-0001-6819-0443"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tuan Vu Ho","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Japan","Japan Advanced Institute of Science & Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Japan Advanced Institute of Science & Technology, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Akagi","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Japan","Japan Advanced Institute of Science & Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Japan Advanced Institute of Science & Technology, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083304186"],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.5779,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77254716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"3","issue":null,"first_page":"106","last_page":"111"},"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":0.9984999895095825,"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":0.987500011920929,"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/autoencoder","display_name":"Autoencoder","score":0.9300256967544556},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6622162461280823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5967673063278198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3415655493736267},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.18927744030952454}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9300256967544556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6622162461280823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5967673063278198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3415655493736267},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18927744030952454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.jaist.ac.jp:10119/16656","is_oa":false,"landing_page_url":"http://hdl.handle.net/10119/16656","pdf_url":null,"source":{"id":"https://openalex.org/S4406922663","display_name":"JAIST Repository","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W83932636","https://openalex.org/W111057040","https://openalex.org/W1959608418","https://openalex.org/W1967858847","https://openalex.org/W2002268800","https://openalex.org/W2007023536","https://openalex.org/W2120605154","https://openalex.org/W2471520273","https://openalex.org/W2532494225","https://openalex.org/W2576309025","https://openalex.org/W2796495654","https://openalex.org/W2805669069","https://openalex.org/W2963035245","https://openalex.org/W2972388953","https://openalex.org/W6603418825","https://openalex.org/W6640963894"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2145836866","https://openalex.org/W2734887215","https://openalex.org/W4220775285"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,54,90,113,133,186,190],"flexible":[3],"non-parallel":[4,149],"voice":[5,33,188,193],"conversion":[6],"(VC)":[7],"system":[8,97,144,172,183],"that":[9,141],"is":[10,81,145],"capable":[11],"of":[12,39,59,119,199],"both":[13,162],"performing":[14],"speaker":[15,19,50,103,107,117,128,135,167],"adaptation":[16],"and":[17,65,152,166],"controlling":[18],"individuality.":[20,136],"The":[21,116,137],"proposed":[22,95,143,182],"VC":[23,41,96,151],"framework":[24],"aims":[25],"to":[26,30,63,83,104,147,189],"tackle":[27],"the":[28,36,49,67,94,127,155],"inability":[29],"arbitrarily":[31],"modify":[32,66],"characteristics":[34],"in":[35,132,161],"converted":[37,120],"waveform":[38],"conventional":[40,148],"model.":[42],"To":[43],"achieve":[44],"this":[45],"goal,":[46],"we":[47],"use":[48],"embedding":[51,129],"realized":[52],"by":[53,125],"Variational":[55],"Autoencoder":[56],"(VAE)":[57],"instead":[58],"one-hot":[60],"encoded":[61],"vectors":[62],"represent":[64],"target":[68,106,114,178,192],"voice's":[69],"characteristics.":[70],"Neither":[71],"parallel":[72,156],"training":[73,88],"data,":[74],"linguistic":[75],"label":[76],"nor":[77],"time":[78],"alignment":[79],"procedure":[80],"required":[82],"train":[84],"our":[85,142,171,181],"system.":[86],"After":[87],"on":[89],"multi-speaker":[91],"speech":[92,121,164,197],"database,":[93],"can":[98,122,184],"adapt":[99],"an":[100],"arbitrary":[101],"source":[102,187],"any":[105],"using":[108],"only":[109,173],"one":[110,175],"sample":[111,176],"from":[112,177],"speaker.":[115,179],"individuality":[118],"be":[123],"controlled":[124],"modifying":[126],"vectors;":[130],"resulting":[131],"fictitious":[134,191],"experimental":[138],"results":[139],"showed":[140],"similar":[146],"VAE-based":[150],"better":[153],"than":[154],"Gaussian":[157],"Mixture":[158],"Model":[159],"(GMM)":[160],"perceived":[163,196],"naturalness":[165,198],"similarity;":[168],"even":[169],"when":[170],"uses":[174],"Moreover,":[180],"convert":[185],"with":[194],"well":[195],"3.1":[200],"MOS.":[201]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}