{"id":"https://openalex.org/W2946555236","doi":"https://doi.org/10.1109/taslp.2019.2917232","title":"ACVAE-VC: Non-Parallel Voice Conversion With Auxiliary Classifier Variational Autoencoder","display_name":"ACVAE-VC: Non-Parallel Voice Conversion With Auxiliary Classifier Variational Autoencoder","publication_year":2019,"publication_date":"2019-05-25","ids":{"openalex":"https://openalex.org/W2946555236","doi":"https://doi.org/10.1109/taslp.2019.2917232","mag":"2946555236"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2917232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2917232","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/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":true,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3102-0162","affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020693766","display_name":"Takuhiro Kaneko","orcid":"https://orcid.org/0009-0000-8016-5144"},"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":"Takuhiro Kaneko","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106710403","display_name":"Kou Tanaka","orcid":"https://orcid.org/0009-0003-7107-607X"},"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":"Kou Tanaka","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079710814","display_name":"Nobukatsu Hojo","orcid":null},"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":"Nobukatsu Hojo","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001243214"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":10.9816,"has_fulltext":false,"cited_by_count":121,"citation_normalized_percentile":{"value":0.98620679,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"27","issue":"9","first_page":"1432","last_page":"1443"},"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":0.9994000196456909,"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":0.9965999722480774,"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":0.8659268021583557},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8110531568527222},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7447603940963745},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6331923007965088},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6190296411514282},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5184051990509033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4608331322669983},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.27014070749282837}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8659268021583557},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8110531568527222},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7447603940963745},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6331923007965088},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6190296411514282},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5184051990509033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4608331322669983},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27014070749282837},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2019.2917232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2917232","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":87,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W1522301498","https://openalex.org/W1959608418","https://openalex.org/W1974745215","https://openalex.org/W1977362459","https://openalex.org/W2022125261","https://openalex.org/W2041448063","https://openalex.org/W2056852181","https://openalex.org/W2057609679","https://openalex.org/W2086796102","https://openalex.org/W2093450784","https://openalex.org/W2099471712","https://openalex.org/W2105160541","https://openalex.org/W2108501770","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2123771434","https://openalex.org/W2127520494","https://openalex.org/W2142300631","https://openalex.org/W2148846882","https://openalex.org/W2148989240","https://openalex.org/W2150769028","https://openalex.org/W2156142001","https://openalex.org/W2157412983","https://openalex.org/W2161727827","https://openalex.org/W2293049663","https://openalex.org/W2396025094","https://openalex.org/W2471520273","https://openalex.org/W2515020857","https://openalex.org/W2518312472","https://openalex.org/W2519091744","https://openalex.org/W2532494225","https://openalex.org/W2548275288","https://openalex.org/W2567070169","https://openalex.org/W2584032004","https://openalex.org/W2651834199","https://openalex.org/W2747744257","https://openalex.org/W2749651610","https://openalex.org/W2769810959","https://openalex.org/W2800289214","https://openalex.org/W2804998325","https://openalex.org/W2811001736","https://openalex.org/W2887264325","https://openalex.org/W2889329491","https://openalex.org/W2890983311","https://openalex.org/W2902070858","https://openalex.org/W2911708970","https://openalex.org/W2949416428","https://openalex.org/W2950776302","https://openalex.org/W2951939904","https://openalex.org/W2962793481","https://openalex.org/W2962882868","https://openalex.org/W2962896155","https://openalex.org/W2963035245","https://openalex.org/W2963175743","https://openalex.org/W2963226019","https://openalex.org/W2963300588","https://openalex.org/W2963444790","https://openalex.org/W2963539064","https://openalex.org/W2963767194","https://openalex.org/W2963782041","https://openalex.org/W2963970792","https://openalex.org/W2963975282","https://openalex.org/W2964121744","https://openalex.org/W2964167449","https://openalex.org/W2964307104","https://openalex.org/W4289305009","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W4320013936","https://openalex.org/W4391602018","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6675944832","https://openalex.org/W6681953653","https://openalex.org/W6687506355","https://openalex.org/W6711854987","https://openalex.org/W6718140377","https://openalex.org/W6729482032","https://openalex.org/W6731370813","https://openalex.org/W6732429163","https://openalex.org/W6735204497","https://openalex.org/W6745718552","https://openalex.org/W6748409065","https://openalex.org/W6753855596","https://openalex.org/W6754095682","https://openalex.org/W6756159577"],"related_works":["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/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W4321789545","https://openalex.org/W2049864679"],"abstract_inverted_index":{"This":[0,110],"paper":[1],"proposes":[2],"a":[3,10,117,224,228],"non-parallel":[4,210],"voice":[5,130],"conversion":[6,49,91,231],"(VC)":[7],"method":[8,25,207],"using":[9,182,223],"variant":[11],"of":[12,61,132,159,179,193],"the":[13,38,45,53,57,72,78,81,90,97,105,119,129,150,156,160,167,176,183,205],"conditional":[14,95],"variational":[15],"autoencoder":[16],"(VAE)":[17],"called":[18],"an":[19,145,217],"auxiliary":[20,146],"classifier":[21,147],"VAE.":[22],"The":[23],"proposed":[24,206],"has":[26],"two":[27],"key":[28],"features.":[29],"First,":[30],"it":[31,67],"adopts":[32],"fully":[33],"convolutional":[34],"architectures":[35],"to":[36,75,103,174,216],"construct":[37],"encoder":[39,98,151,185],"and":[40,63,99,148,152,186,188,198,213],"decoder":[41,100,153,161,187],"networks":[42,46],"so":[43,154],"that":[44,51,77,155,204],"can":[47,111,140],"learn":[48],"rules":[50],"capture":[52],"time":[54],"dependencies":[55],"in":[56,80,89,115,191,227],"acoustic":[58],"feature":[59,177],"sequences":[60],"source":[62],"target":[64],"speech.":[65],"Second,":[66],"uses":[68],"information-theoretic":[69],"regularization":[70],"for":[71],"model":[73],"training":[74,149],"ensure":[76],"information":[79],"attribute":[82,106,120,157],"class":[83,107,121],"label":[84,108,122],"will":[85,123],"not":[86],"be":[87,112,141],"lost":[88],"process.":[92],"With":[93],"regular":[94],"VAEs,":[96],"are":[101,163],"free":[102],"ignore":[104],"input.":[109],"problematic":[113],"since":[114],"such":[116],"situation,":[118],"have":[124],"little":[125],"effect":[126],"on":[127],"controlling":[128],"characteristics":[131],"input":[133,180],"speech":[134,181],"at":[135],"test":[136],"time.":[137],"Such":[138],"situations":[139],"avoided":[142],"by":[143,166],"introducing":[144],"classes":[158],"outputs":[162],"correctly":[164],"predicted":[165],"classifier.":[168],"We":[169,201],"also":[170],"present":[171],"several":[172],"ways":[173],"convert":[175],"sequence":[178],"trained":[184,222],"compare":[189],"them":[190],"terms":[192],"audio":[194],"quality":[195],"through":[196],"objective":[197],"subjective":[199],"evaluations.":[200],"confirmed":[202],"experimentally":[203],"outperformed":[208],"baseline":[209],"VC":[211,220],"systems":[212],"performed":[214],"comparably":[215],"open-source":[218],"parallel":[219,225],"system":[221],"corpus":[226],"speaker":[229],"identity":[230],"task.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":28},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}