{"id":"https://openalex.org/W3097450432","doi":"https://doi.org/10.1587/transinf.2020edp7032","title":"Speech Chain VC: Linking Linguistic and Acoustic Levels via Latent Distinctive Features for RBM-Based Voice Conversion","display_name":"Speech Chain VC: Linking Linguistic and Acoustic Levels via Latent Distinctive Features for RBM-Based Voice Conversion","publication_year":2020,"publication_date":"2020-10-31","ids":{"openalex":"https://openalex.org/W3097450432","doi":"https://doi.org/10.1587/transinf.2020edp7032","mag":"3097450432"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2020edp7032","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2020edp7032","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/11/E103.D_2020EDP7032/_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/E103.D/11/E103.D_2020EDP7032/_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/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":true,"raw_author_name":"Takuya KISHIDA","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"]}]},{"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/I20529979"],"apc_list":null,"apc_paid":null,"fwci":0.2718,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65494983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"E103.D","issue":"11","first_page":"2340","last_page":"2350"},"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/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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/T10860","display_name":"Speech and Audio Processing","score":0.9939000010490417,"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":0.8207638263702393},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6598888039588928},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.498948335647583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38585931062698364},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.327450692653656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207638263702393},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6598888039588928},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.498948335647583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38585931062698364},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.327450692653656},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2020edp7032","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2020edp7032","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/11/E103.D_2020EDP7032/_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.2020edp7032","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2020edp7032","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/11/E103.D_2020EDP7032/_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":[],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4227499671","display_name":null,"funder_award_id":"KAKENHI Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4827429566","display_name":null,"funder_award_id":"Grant Numbers","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G497407216","display_name":"Speech Representation Using Emotion-Speaker Controllable Probabilistic Model Based on Extended Boltzmann Distribution","funder_award_id":"18K18069","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G509532826","display_name":"Development of speech enhancement methods for conveying emotions equivalent to face-to-face communication","funder_award_id":"19K20618","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5786340949","display_name":null,"funder_award_id":"KAKENHI Grant Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3097450432.pdf","grobid_xml":"https://content.openalex.org/works/W3097450432.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W2009272428","https://openalex.org/W2017313821","https://openalex.org/W2120605154","https://openalex.org/W2136936677","https://openalex.org/W2150769028","https://openalex.org/W2152205330","https://openalex.org/W2169878657","https://openalex.org/W2395750323","https://openalex.org/W2471520273","https://openalex.org/W2475998840","https://openalex.org/W2515028311","https://openalex.org/W2532494225","https://openalex.org/W2574092538","https://openalex.org/W2594475271","https://openalex.org/W2651834199","https://openalex.org/W2657631929","https://openalex.org/W2804998325","https://openalex.org/W2888922217","https://openalex.org/W2902070858","https://openalex.org/W2937579788","https://openalex.org/W2962793481","https://openalex.org/W2963035245","https://openalex.org/W2963073614","https://openalex.org/W2963539064","https://openalex.org/W2963971656","https://openalex.org/W2965648961","https://openalex.org/W2969049672","https://openalex.org/W2972667718","https://openalex.org/W3020524185"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0],"paper":[1,201],"proposes":[2,202],"a":[3,10,43,164,221,229],"voice":[4],"conversion":[5,153],"(VC)":[6],"method":[7,158],"based":[8,239],"on":[9,171,240],"model":[11,167,183],"that":[12,57,137,162,185,219],"links":[13,100],"linguistic":[14],"and":[15,84,112,121,244],"acoustic":[16,65,113],"representations":[17,173],"via":[18],"latent":[19,122],"phonological":[20,74,123,194],"distinctive":[21,124,195],"features.":[22,196],"Our":[23],"method,":[24],"called":[25],"speech":[26,36,39,142,180,211],"chain":[27,44,95,181,212],"VC,":[28],"is":[29,67,76,224],"inspired":[30],"by":[31,101,208],"the":[32,35,48,52,64,140,147,156,172,175,179,188,210,225,232],"concept":[33],"of":[34,42,45,118,139,155,163,174,178,187,199],"chain,":[37],"where":[38,73,85],"communication":[40],"consists":[41],"events":[46],"linking":[47],"speaker's":[49,246],"brain":[50],"with":[51,127,146],"listener's":[53],"brain.":[54],"We":[55],"assume":[56],"speaker":[58,223],"identity":[59],"information,":[60],"which":[61],"appears":[62],"in":[63,69],"level,":[66],"embedded":[68],"two":[70,116],"steps":[71],"\u2014":[72],"information":[75],"encoded":[77],"into":[78],"articulatory":[79,86,128],"movements":[80,87,129],"(linguistic":[81],"to":[82,92,161,193,204],"physiological)":[83],"generate":[88],"sound":[89],"waves":[90],"(physiological":[91],"acoustic).":[93],"Speech":[94],"VC":[96,182,207,213,238],"represents":[97],"these":[98],"event":[99],"using":[102,209],"an":[103],"adaptive":[104],"restricted":[105],"Boltzmann":[106],"machine":[107],"(ARBM)":[108],"introducing":[109],"phoneme":[110],"labels":[111],"features":[114,125],"as":[115,130,228],"classes":[117],"visible":[119],"units":[120,190],"associated":[126],"hidden":[131,176,189],"units.":[132],"Subjective":[133,215],"evaluation":[134,216],"experiments":[135,217],"showed":[136,218],"intelligibility":[138],"converted":[141],"significantly":[143],"improved":[144],"compared":[145],"conventional":[148],"ARBM-based":[149],"method.":[150,169],"The":[151],"speaker-identity":[152],"quality":[154],"proposed":[157,233],"was":[159],"comparable":[160],"Gaussian":[165],"mixture":[166],"(GMM)-based":[168],"Analyses":[170],"layer":[177],"supported":[184],"some":[186],"actually":[191],"correspond":[192],"Final":[197],"part":[198],"this":[200],"approaches":[203],"achieve":[205,236],"one-shot":[206,237],"model.":[214],"when":[220],"target":[222,245],"same":[226],"gender":[227],"source":[230,243],"speaker,":[231],"methods":[234],"can":[235],"each":[241],"single":[242],"utterance.":[247]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}