{"id":"https://openalex.org/W4372260197","doi":"https://doi.org/10.1109/icassp49357.2023.10096901","title":"JSV-VC: Jointly Trained Speaker Verification and Voice Conversion Models","display_name":"JSV-VC: Jointly Trained Speaker Verification and Voice Conversion Models","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260197","doi":"https://doi.org/10.1109/icassp49357.2023.10096901"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096901","doi":"https://doi.org/10.1109/icassp49357.2023.10096901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096901","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5101792863","display_name":"Shogo Seki","orcid":"https://orcid.org/0009-0007-3990-3740","observed_orcids":["https://orcid.org/0009-0007-3990-3740","https://orcid.org/0000-0001-8284-188X"]},"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":"Shogo Seki","raw_affiliation_strings":["NTT Corporation,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162","observed_orcids":["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 Corporation,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004248530","display_name":"Kou Tanaka","orcid":null,"observed_orcids":[]},"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 Corporation,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020693766","display_name":"Takuhiro Kaneko","orcid":"https://orcid.org/0009-0000-8016-5144","observed_orcids":["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 Corporation,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.2209,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42295735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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/T10863","display_name":"Voice and Speech Disorders","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/voice-conversion","display_name":"voice conversion","score":0.9679999947547913},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"speaker verification","score":0.996999979019165},{"id":"https://openalex.org/keywords/joint-training","display_name":"joint training","score":0.6740000247955322},{"id":"https://openalex.org/keywords/variational-autoencoder","display_name":"variational autoencoder","score":0.9769999980926514},{"id":"https://openalex.org/keywords/non-parallel-voice-conversion","display_name":"non-parallel voice conversion","score":0.7020000219345093},{"id":"https://openalex.org/keywords/speaker-embedding","display_name":"speaker embedding","score":0.9279999732971191}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8034979104995728},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7821345925331116},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6233676671981812},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5829691886901855}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096901","doi":"https://doi.org/10.1109/icassp49357.2023.10096901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096901","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W1509691205","https://openalex.org/W1959608418","https://openalex.org/W2022125261","https://openalex.org/W2105160541","https://openalex.org/W2108501770","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2126143605","https://openalex.org/W2142300631","https://openalex.org/W2156142001","https://openalex.org/W2532494225","https://openalex.org/W2613904329","https://openalex.org/W2768626898","https://openalex.org/W2804998325","https://openalex.org/W2889061305","https://openalex.org/W2899877258","https://openalex.org/W2937579788","https://openalex.org/W2945478979","https://openalex.org/W2946555236","https://openalex.org/W2962788625","https://openalex.org/W2962793481","https://openalex.org/W2963539064","https://openalex.org/W2972544500","https://openalex.org/W2972659941","https://openalex.org/W2972667718","https://openalex.org/W2992384298","https://openalex.org/W3015338123","https://openalex.org/W3034420534","https://openalex.org/W3095936335","https://openalex.org/W3098403858","https://openalex.org/W3100696337","https://openalex.org/W3113687514","https://openalex.org/W3118753411","https://openalex.org/W3162512456","https://openalex.org/W3162879338","https://openalex.org/W3163475957","https://openalex.org/W4221145935","https://openalex.org/W4320013936","https://openalex.org/W6678506862","https://openalex.org/W6755930846","https://openalex.org/W6761382815","https://openalex.org/W6784504775"],"related_works":["https://openalex.org/W3115500749","https://openalex.org/W4375868976","https://openalex.org/W3162414783","https://openalex.org/W3095953768","https://openalex.org/W4385975838","https://openalex.org/W4416034188","https://openalex.org/W3163654539","https://openalex.org/W4411858383","https://openalex.org/W3144417991","https://openalex.org/W4291302210"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,34,43,54,59],"variational":[4],"autoencoder":[5],"(VAE)-based":[6],"method":[7],"for":[8,42,73],"voice":[9],"conversion":[10,79],"(VC)":[11],"on":[12],"arbitrary":[13],"source-target":[14],"speaker":[15,30,35,68,110],"pairs":[16],"without":[17],"parallel":[18],"corpora,":[19],"i.e.,":[20],"non-parallel":[21],"any-to-any":[22,141],"VC.":[23],"One":[24],"typical":[25],"approach":[26],"is":[27,49,99,105,119],"to":[28,52,77,123],"use":[29],"embeddings":[31,69,126],"obtained":[32],"from":[33],"verification":[36],"(SV)":[37],"model":[38,98,118],"as":[39,107],"the":[40,85,108,112,116,130],"condition":[41],"VC":[44,63,74,91,97,131,142],"model.":[45,132],"However,":[46],"converted":[47,103],"speech":[48,104],"not":[50,71],"guaranteed":[51],"reflect":[53],"target":[55,109],"speaker\u2019s":[56],"characteristics":[57],"in":[58,111,121],"naive":[60],"combination":[61],"of":[62],"and":[64,92,128,145],"SV":[65,93,113,117],"models.":[66],"Moreover,":[67],"are":[70],"designed":[72],"problems,":[75],"leading":[76],"suboptimal":[78],"performance.":[80],"To":[81],"address":[82],"these":[83],"issues,":[84],"proposed":[86],"method,":[87],"JSV-VC,":[88],"trains":[89],"both":[90],"models":[94],"jointly.":[95],"The":[96,133],"trained":[100,120],"so":[101],"that":[102,137],"verified":[106],"model,":[114],"while":[115],"order":[122],"output":[124],"consistent":[125],"before":[127],"after":[129],"experimental":[134],"evaluation":[135],"reveals":[136],"JSV-VC":[138],"outperforms":[139],"conventional":[140],"methods":[143],"quantitatively":[144],"qualitatively.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-05-07T00:00:00"}
