{"id":"https://openalex.org/W4407873422","doi":"https://doi.org/10.1587/transinf.2024edp7206","title":"Fast and Lightweight Non-Parallel Voice Conversion Based on Free-Energy Minimization of Speaker-Conditional Restricted Boltzmann Machine","display_name":"Fast and Lightweight Non-Parallel Voice Conversion Based on Free-Energy Minimization of Speaker-Conditional Restricted Boltzmann Machine","publication_year":2025,"publication_date":"2025-02-24","ids":{"openalex":"https://openalex.org/W4407873422","doi":"https://doi.org/10.1587/transinf.2024edp7206"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2024edp7206","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edp7206","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/8/E108.D_2024EDP7206/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/8/E108.D_2024EDP7206/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113634113","display_name":"Takuya Kishida","orcid":null},"institutions":[{"id":"https://openalex.org/I87572379","display_name":"Aichi Shukutoku University","ror":"https://ror.org/00z9wtp09","country_code":"JP","type":"education","lineage":["https://openalex.org/I87572379"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takuya KISHIDA","raw_affiliation_strings":["Faculty of Human Informatics, Aichi Shukutoku University"],"affiliations":[{"raw_affiliation_string":"Faculty of Human Informatics, Aichi Shukutoku University","institution_ids":["https://openalex.org/I87572379"]}]},{"author_position":"last","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 Informatics and Engineering, The University of Electro-Communications"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics and Engineering, The University of Electro-Communications","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113634113"],"corresponding_institution_ids":["https://openalex.org/I87572379"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02686934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"E108.D","issue":"8","first_page":"1001","last_page":"1010"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9926999807357788,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9926999807357788,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9757000207901001,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9466999769210815,"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/computer-science","display_name":"Computer science","score":0.8866006135940552},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.7765899896621704},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.5827804803848267},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5401020050048828},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.48157548904418945},{"id":"https://openalex.org/keywords/restricted-boltzmann-machine","display_name":"Restricted Boltzmann machine","score":0.4520813822746277},{"id":"https://openalex.org/keywords/energy-minimization","display_name":"Energy minimization","score":0.4337715804576874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.312358558177948},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20102092623710632},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05475172400474548}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8866006135940552},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.7765899896621704},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.5827804803848267},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5401020050048828},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.48157548904418945},{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.4520813822746277},{"id":"https://openalex.org/C14961307","wikidata":"https://www.wikidata.org/wiki/Q5377176","display_name":"Energy minimization","level":2,"score":0.4337715804576874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.312358558177948},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20102092623710632},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05475172400474548},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2024edp7206","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edp7206","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/8/E108.D_2024EDP7206/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2024edp7206","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edp7206","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/8/E108.D_2024EDP7206/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8799999952316284,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1710176601","display_name":"\u4ecf\u6559\u306b\u65bc\u3051\u308b\u54f2\u5b66\u7684\u8af8\u6982\u5ff5\u306e\u5206\u6790","funder_award_id":"11161","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8224511031","display_name":null,"funder_award_id":"24H00715","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8346283936","display_name":"\u6df1\u5c64\u30a8\u30cd\u30eb\u30ae\u30fc\u30d9\u30fc\u30b9\u30e2\u30c7\u30eb\u306b\u3088\u308b\u5275\u9020\u7684\u58f0\u8cea\u5909\u63db\u306e\u7814\u7a76","funder_award_id":"23K11161","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407873422.pdf","grobid_xml":"https://content.openalex.org/works/W4407873422.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2056133372","https://openalex.org/W2136922672","https://openalex.org/W2136936677","https://openalex.org/W2291425271","https://openalex.org/W2471520273","https://openalex.org/W2475998840","https://openalex.org/W2752796333","https://openalex.org/W2902070858","https://openalex.org/W2937579788","https://openalex.org/W2945478979","https://openalex.org/W2947590261","https://openalex.org/W2959300817","https://openalex.org/W2962793481","https://openalex.org/W2963539064","https://openalex.org/W2963767194","https://openalex.org/W2969049672","https://openalex.org/W3015434413","https://openalex.org/W3034058691","https://openalex.org/W3035384201","https://openalex.org/W3036167779","https://openalex.org/W3097450432","https://openalex.org/W3204602440","https://openalex.org/W4297841639","https://openalex.org/W4311000453","https://openalex.org/W4392979699"],"related_works":["https://openalex.org/W2952018105","https://openalex.org/W2916681395","https://openalex.org/W4283272532","https://openalex.org/W2119341610","https://openalex.org/W2556473569","https://openalex.org/W2193475944","https://openalex.org/W4302433642","https://openalex.org/W2529583158","https://openalex.org/W2551541394","https://openalex.org/W2892911634"],"abstract_inverted_index":{"In":[0,126,152],"this":[1],"paper,":[2],"we":[3,100],"propose":[4],"a":[5,20,41,56,69,114],"fast":[6],"and":[7,44,76,143],"lightweight":[8],"non-parallel":[9],"voice":[10],"conversion":[11,138],"method":[12,27,132,161],"based":[13],"on":[14,40],"minimizing":[15],"the":[16,33,47,65,77,89,93,97,103,107,130,156,159],"free":[17,53,108],"energy":[18,54,109],"of":[19,36,79,92,106,149,158,166],"restricted":[21],"Boltzmann":[22],"machine":[23],"(RBM).":[24],"The":[25],"proposed":[26,131,160],"employs":[28],"an":[29],"RBM":[30,66],"that":[31,102,165],"learns":[32],"generative":[34],"probability":[35],"acoustic":[37,49],"features":[38,50],"conditioned":[39],"target":[42],"speaker":[43],"iteratively":[45],"updates":[46,121],"input":[48],"until":[51],"their":[52],"reaches":[55],"local":[57],"minimum,":[58],"resulting":[59],"in":[60,147,168],"converted":[61],"features.":[62],"Due":[63],"to":[64,73,164],"framework,":[67],"only":[68],"few":[70],"hyperparameters":[71],"need":[72],"be":[74,111],"set,":[75],"number":[78],"training":[80],"parameters":[81],"is":[82],"minimal,":[83],"ensuring":[84],"stable":[85],"training.":[86],"When":[87],"determining":[88],"step":[90],"size":[91],"update":[94],"formula":[95],"using":[96],"Newton-Raphson":[98],"method,":[99],"found":[101],"Hessian":[104],"matrix":[105],"can":[110],"approximated":[112],"by":[113],"diagonal":[115],"matrix.":[116],"This":[117],"allows":[118],"for":[119],"efficient":[120],"with":[122,141],"minimal":[123],"computational":[124],"costs.":[125],"objective":[127],"evaluation":[128,154],"experiments,":[129,155],"demonstrated":[133],"approximately":[134],"4.5":[135],"times":[136],"faster":[137],"speed":[139],"compared":[140],"StarGAN-VC":[142,146,167],"also":[144],"outperformed":[145],"terms":[148],"Mel-cepstrum":[150],"distortion.":[151],"subjective":[153],"performance":[157],"was":[162],"comparable":[163],"similarity":[169],"mean":[170],"opinion":[171],"score.":[172]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
