{"id":"https://openalex.org/W2542435598","doi":"https://doi.org/10.1587/transinf.2016edp7234","title":"Improvements of Voice Timbre Control Based on Perceived Age in Singing Voice Conversion","display_name":"Improvements of Voice Timbre Control Based on Perceived Age in Singing Voice Conversion","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2542435598","doi":"https://doi.org/10.1587/transinf.2016edp7234","mag":"2542435598"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2016edp7234","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016edp7234","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/11/E99.D_2016EDP7234/_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/E99.D/11/E99.D_2016EDP7234/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037417355","display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0001-7801-147X"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro KOBAYASHI","raw_affiliation_strings":["Nara Institute of Science and Technology (NAIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology (NAIST)","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki TODA","raw_affiliation_strings":["Information Technology Center, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039431216","display_name":"Tomoyasu Nakano","orcid":"https://orcid.org/0000-0001-8014-2209"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoyasu NAKANO","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST)","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030650456","display_name":"Masataka Goto","orcid":"https://orcid.org/0000-0003-1167-0977"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masataka GOTO","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST)","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi NAKAMURA","raw_affiliation_strings":["Nara Institute of Science and Technology (NAIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology (NAIST)","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07465516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"E99.D","issue":"11","first_page":"2767","last_page":"2777"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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/singing","display_name":"Singing","score":0.8982787132263184},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.8741257190704346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.68875652551651},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6742408871650696},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5333872437477112},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.49424365162849426},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.4850546717643738},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4706403911113739},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4128715693950653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2972772717475891},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.27173513174057007},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18731608986854553}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8982787132263184},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8741257190704346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.68875652551651},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6742408871650696},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5333872437477112},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.49424365162849426},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.4850546717643738},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4706403911113739},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4128715693950653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2972772717475891},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27173513174057007},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18731608986854553},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2016edp7234","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016edp7234","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/11/E99.D_2016EDP7234/_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.2016edp7234","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016edp7234","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/11/E99.D_2016EDP7234/_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":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G2327824500","display_name":"Development of augmented speech production techniques based on combination of statistical approaches and speech production modeling approaches","funder_award_id":"26280060","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G234358013","display_name":"\u6b4c\u58f0\u77e5\u899a\u3092\u8003\u616e\u3057\u305f\u7d71\u8a08\u7684\u6b4c\u58f0\u58f0\u8cea\u5236\u5fa1\u6cd5\u306b\u95a2\u3059\u308b\u7814\u7a76","funder_award_id":"16J10726","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/W2542435598.pdf","grobid_xml":"https://content.openalex.org/works/W2542435598.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W33533989","https://openalex.org/W49412823","https://openalex.org/W1482298176","https://openalex.org/W1581272224","https://openalex.org/W1590808459","https://openalex.org/W1963637322","https://openalex.org/W2009926692","https://openalex.org/W2020343820","https://openalex.org/W2049686551","https://openalex.org/W2070513494","https://openalex.org/W2077865492","https://openalex.org/W2120605154","https://openalex.org/W2129082420","https://openalex.org/W2129142580","https://openalex.org/W2130081501","https://openalex.org/W2145892079","https://openalex.org/W2154920538","https://openalex.org/W2156142001","https://openalex.org/W2161476805","https://openalex.org/W2168790345","https://openalex.org/W2293635543","https://openalex.org/W2294038178","https://openalex.org/W2395578248","https://openalex.org/W2401296648","https://openalex.org/W2401318443","https://openalex.org/W2763280966","https://openalex.org/W4245284779"],"related_works":["https://openalex.org/W4288088492","https://openalex.org/W2982290989","https://openalex.org/W1516392727","https://openalex.org/W2001828059","https://openalex.org/W2031321541","https://openalex.org/W4210742324","https://openalex.org/W1967908900","https://openalex.org/W2603569513","https://openalex.org/W2898292629","https://openalex.org/W4289829928"],"abstract_inverted_index":{"As":[0],"one":[1,59],"of":[2,12,40,48,60,69,75,99,114,136,144,155,203,221,259,267,275],"the":[3,10,28,37,46,49,54,61,70,91,100,111,137,145,167,179,188,200,204,222,243,251,260,268,273,276],"techniques":[4],"enabling":[5],"individual":[6,107],"singers":[7,108],"to":[8,65,109,153,165,177,198,218,240],"produce":[9],"varieties":[11],"voice":[13,22,67,77,92,148],"timbre":[14,23,93],"beyond":[15],"their":[16,115,121],"own":[17,116,122],"physical":[18],"constraints,":[19],"a":[20,41,81,97,133,156,174,193,208,228,236,255,263,281],"statistical":[21,76],"control":[24],"technique":[25],"based":[26,214,233],"on":[27,215,234],"perceived":[29,38,52,101,112,138,205,261],"age":[30,39,47,139],"has":[31],"been":[32],"developed.":[33],"In":[34],"this":[35],"technique,":[36],"singing":[42,71,117,147,158,224,270],"voice,":[43,271],"which":[44,88],"is":[45,56,140,149],"singer":[50,123,163,176],"as":[51,58,171,285],"by":[53,96,173],"listener,":[55],"used":[57],"intuitively":[62],"understandable":[63],"measures":[64],"describe":[66],"characteristics":[68],"voice.":[72],"The":[73,246],"use":[74],"conversion":[78],"(SVC)":[79],"with":[80],"singer-dependent":[82,180,244],"multiple-regression":[83],"Gaussian":[84],"mixture":[85],"model":[86],"(MR-GMM),":[87],"effectively":[89],"models":[90],"variations":[94],"caused":[95],"change":[98],"age,":[102,262],"makes":[103],"it":[104],"possible":[105],"for":[106],"manipulate":[110],"ages":[113],"voices":[118],"while":[119],"retaining":[120],"identities.":[124],"However,":[125],"there":[126],"still":[127],"remain":[128],"several":[129],"issues;":[130],"e.g.,":[131],"1)":[132,192],"controllable":[134,201,257],"range":[135,202,258],"limited;":[141],"2)":[142,207],"quality":[143,220,265],"converted":[146,223,269],"significantly":[150],"degraded":[151],"compared":[152],"that":[154,250],"natural":[157],"voice;":[159,225],"and":[160,226,272],"3)":[161,227],"each":[162],"needs":[164],"sing":[166],"same":[168],"phrase":[169],"set":[170],"sung":[172],"reference":[175],"develop":[178,242],"MR-GMM.":[181,245],"To":[182],"address":[183],"these":[184],"issues,":[185],"we":[186],"propose":[187],"following":[189],"three":[190],"methods;":[191],"method":[194,209,232],"using":[195,210,279],"gender-dependent":[196],"modeling":[197],"expand":[199],"age;":[206],"direct":[211],"waveform":[212],"modification":[213],"spectrum":[216],"differential":[217],"improve":[219],"rapid":[229],"unsupervised":[230],"adaptation":[231,286],"maximum":[235],"posteriori":[237],"(MAP)":[238],"estimation":[239],"easily":[241],"experimental":[247],"results":[248],"show":[249],"proposed":[252],"methods":[253],"achieve":[254],"wider":[256],"significant":[264],"improvement":[266],"development":[274],"singer-dependnet":[277],"MR-GMM":[278],"only":[280],"few":[282],"arbitrary":[283],"phrases":[284],"data.":[287]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
