{"id":"https://openalex.org/W2475998840","doi":"https://doi.org/10.1109/taslp.2016.2593263","title":"Non-Parallel Training in Voice Conversion Using an Adaptive Restricted Boltzmann Machine","display_name":"Non-Parallel Training in Voice Conversion Using an Adaptive Restricted Boltzmann Machine","publication_year":2016,"publication_date":"2016-07-19","ids":{"openalex":"https://openalex.org/W2475998840","doi":"https://doi.org/10.1109/taslp.2016.2593263","mag":"2475998840"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2593263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2593263","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":true,"oa_status":"green","oa_url":"https://uec.repo.nii.ac.jp/record/9027/files/vcarbm.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041887072","display_name":"Toru Nakashika","orcid":"https://orcid.org/0000-0003-1863-6771"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toru Nakashika","raw_affiliation_strings":["Graduate School of Information Systems, University of Electro-Communications, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Systems, University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009283470","display_name":"Tetsuya Takiguchi","orcid":"https://orcid.org/0000-0001-5005-7679"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Takiguchi","raw_affiliation_strings":["Organization of Advanced Science and Technology, Kobe University, Kobe, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Organization of Advanced Science and Technology, Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008413640","display_name":"Yasuhiro Minami","orcid":"https://orcid.org/0000-0003-3514-4285"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuhiro Minami","raw_affiliation_strings":["Graduate School of Information Systems, University of Electro-Communications, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Systems, University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":20.4412,"has_fulltext":true,"cited_by_count":63,"citation_normalized_percentile":{"value":0.99189979,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"24","issue":"11","first_page":"2032","last_page":"2045"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9994999766349792,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.7869781255722046},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.712576687335968},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.44781896471977234},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.4465062618255615},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.44204580783843994},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4138854146003723},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4114309251308441},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35212236642837524},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32684001326560974},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15551531314849854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7869781255722046},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.712576687335968},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.44781896471977234},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.4465062618255615},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.44204580783843994},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4138854146003723},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4114309251308441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35212236642837524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32684001326560974},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15551531314849854},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2016.2593263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2593263","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"},{"id":"pmh:oai:irdb.nii.ac.jp:00931:0003987939","is_oa":true,"landing_page_url":"https://uec.repo.nii.ac.jp/records/9027","pdf_url":"https://uec.repo.nii.ac.jp/record/9027/files/vcarbm.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:00931:0003987939","is_oa":true,"landing_page_url":"https://uec.repo.nii.ac.jp/records/9027","pdf_url":"https://uec.repo.nii.ac.jp/record/9027/files/vcarbm.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2475998840.pdf","grobid_xml":"https://content.openalex.org/works/W2475998840.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W10800834","https://openalex.org/W17772838","https://openalex.org/W49412823","https://openalex.org/W152891837","https://openalex.org/W1588266896","https://openalex.org/W1605997703","https://openalex.org/W1791038712","https://openalex.org/W1950777589","https://openalex.org/W1963778986","https://openalex.org/W1969728648","https://openalex.org/W1972420736","https://openalex.org/W1977362459","https://openalex.org/W2009272428","https://openalex.org/W2017425464","https://openalex.org/W2022125261","https://openalex.org/W2067175291","https://openalex.org/W2086796102","https://openalex.org/W2099866409","https://openalex.org/W2105160541","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2129863563","https://openalex.org/W2136922672","https://openalex.org/W2136936677","https://openalex.org/W2137313500","https://openalex.org/W2153057929","https://openalex.org/W2156142001","https://openalex.org/W2157412983","https://openalex.org/W2161476805","https://openalex.org/W2169878657","https://openalex.org/W2294351487","https://openalex.org/W2400505377","https://openalex.org/W2401544731","https://openalex.org/W2404109308","https://openalex.org/W2404719220","https://openalex.org/W2407110532","https://openalex.org/W2577350056","https://openalex.org/W2913399920","https://openalex.org/W4244017338","https://openalex.org/W4285719527","https://openalex.org/W6600438624","https://openalex.org/W6600709279","https://openalex.org/W6602007935","https://openalex.org/W6635216677","https://openalex.org/W6638407692","https://openalex.org/W6680279962","https://openalex.org/W6696767757","https://openalex.org/W6713064456","https://openalex.org/W6713088551","https://openalex.org/W6713304735","https://openalex.org/W6713858911","https://openalex.org/W6732045268"],"related_works":["https://openalex.org/W2916681395","https://openalex.org/W2529583158","https://openalex.org/W1575733688","https://openalex.org/W2963348254","https://openalex.org/W1641020902","https://openalex.org/W3128475979","https://openalex.org/W2133316674","https://openalex.org/W1968450737","https://openalex.org/W3121130100","https://openalex.org/W2142815029"],"abstract_inverted_index":{"In":[0,130,183],"this":[1],"paper,":[2],"we":[3,133],"present":[4],"a":[5,23,122,139,157,187],"voice":[6],"conversion":[7,185],"(VC)":[8],"method":[9,243],"that":[10,151,204,223,244],"does":[11],"not":[12,117],"use":[13,65,119],"any":[14],"parallel":[15,48,67,120,246],"data":[16,52,68,76,247],"while":[17,34],"training":[18,70,80,136],"the":[19,36,42,54,60,64,75,79,84,88,95,100,184,198,206,217,237],"model.":[20],"VC":[21,44,116],"is":[22,32,91,125,191,201,213],"technique":[24,142],"where":[25,163],"only":[26,92],"speaker-specific":[27],"information":[28,38,165,168,200],"in":[29,69,99,105,115,248],"source":[30,55],"speech":[31,51,152,189,212],"converted":[33],"keeping":[35],"phonological":[37,146,164,194],"unchanged.":[39],"Most":[40],"of":[41,50,66,205,236],"existing":[43],"methods":[45],"rely":[46],"on":[47,138],"data-pairs":[49],"from":[53,156],"and":[56,102,143,166,173,195,209,230,250],"target":[57],"speakers":[58],"uttering":[59],"same":[61],"sentences.":[62],"However,":[63],"causes":[71],"several":[72],"problems:":[73],"1)":[74],"used":[77,98,245],"for":[78],"are":[81,154,169,176],"limited":[82],"to":[83,94,118,128,234],"predefined":[85],"sentences,":[86],"2)":[87],"trained":[89,178],"model":[90],"applied":[93],"speaker":[96,140,180],"pair":[97],"training,":[101],"3)":[103],"mismatches":[104],"alignment":[106],"may":[107],"occur.":[108],"Although":[109],"it":[110],"is,":[111],"thus,":[112],"fairly":[113],"preferable":[114],"data,":[121],"nonparallel":[123,135,228],"approach":[124,149,225],"considered":[126],"difficult":[127],"learn.":[129],"our":[131,224],"approach,":[132,229],"achieve":[134],"based":[137],"adaptation":[141],"capturing":[144],"latent":[145],"information.":[147],"This":[148],"assumes":[150],"signals":[153],"produced":[155,231],"restricted":[158],"Boltzmann":[159],"machine-based":[160],"probabilistic":[161],"model,":[162],"speaker-related":[167,196,199],"defined":[170],"explicitly.":[171],"Speaker-independent":[172],"speaker-dependent":[174],"parameters":[175],"simultaneously":[177],"under":[179],"adaptive":[181],"training.":[182],"stage,":[186],"given":[188],"signal":[190],"decomposed":[192],"into":[193],"information,":[197],"replaced":[202],"with":[203],"desired":[207],"speaker,":[208],"then":[210],"voice-converted":[211],"obtained":[214],"by":[215],"mixing":[216],"two.":[218],"Our":[219],"experimental":[220],"results":[221,232],"showed":[222],"outperformed":[226],"another":[227],"similar":[233],"those":[235],"popular":[238],"conventional":[239],"Gaussian":[240],"mixture":[241],"models-based":[242],"subjective":[249],"objective":[251],"criteria.":[252]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":10}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}