{"id":"https://openalex.org/W2524591323","doi":"https://doi.org/10.1587/transinf.2016slp0020","title":"A Statistical Sample-Based Approach to GMM-Based Voice Conversion Using Tied-Covariance Acoustic Models","display_name":"A Statistical Sample-Based Approach to GMM-Based Voice Conversion Using Tied-Covariance Acoustic Models","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2524591323","doi":"https://doi.org/10.1587/transinf.2016slp0020","mag":"2524591323"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2016slp0020","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016slp0020","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0020/_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/10/E99.D_2016SLP0020/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"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":true,"raw_author_name":"Shinnosuke TAKAMICHI","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology","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"],"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000692949","display_name":"Graham Neubig","orcid":null},"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":"Graham NEUBIG","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"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":"Sakriani SAKTI","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]},{"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":["Graduate School of Information Science, Nara Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5013050263"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.4417,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79634375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"E99.D","issue":"10","first_page":"2490","last_page":"2498"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9979000091552734,"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":0.9781000018119812,"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/mixture-model","display_name":"Mixture model","score":0.8410091400146484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8156272172927856},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7284741401672363},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6572372913360596},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6065091490745544},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5803290605545044},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4262702763080597},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42480623722076416},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4228455722332001},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4161505103111267}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.8410091400146484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8156272172927856},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7284741401672363},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6572372913360596},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6065091490745544},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5803290605545044},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4262702763080597},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42480623722076416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4228455722332001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4161505103111267},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2016slp0020","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016slp0020","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0020/_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.2016slp0020","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016slp0020","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0020/_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/G3236194794","display_name":null,"funder_award_id":"Grant-in-Aid","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/G4874944895","display_name":null,"funder_award_id":"-in-Aid","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5396239172","display_name":null,"funder_award_id":"Grant-in-Aid for JSPS Fellows","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6897158703","display_name":null,"funder_award_id":"JSPS Fellows","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/W2524591323.pdf","grobid_xml":"https://content.openalex.org/works/W2524591323.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W164845301","https://openalex.org/W187033940","https://openalex.org/W564913581","https://openalex.org/W1120805016","https://openalex.org/W1513358034","https://openalex.org/W1517202054","https://openalex.org/W1523372075","https://openalex.org/W1558606374","https://openalex.org/W1568585903","https://openalex.org/W1581272224","https://openalex.org/W1789888671","https://openalex.org/W1963627370","https://openalex.org/W1991682319","https://openalex.org/W2004299580","https://openalex.org/W2005438552","https://openalex.org/W2019849101","https://openalex.org/W2023694213","https://openalex.org/W2049686551","https://openalex.org/W2077865492","https://openalex.org/W2095134692","https://openalex.org/W2100140000","https://openalex.org/W2109444541","https://openalex.org/W2111284386","https://openalex.org/W2120605154","https://openalex.org/W2121095010","https://openalex.org/W2134383396","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2156142001","https://openalex.org/W2159528802","https://openalex.org/W2179117922","https://openalex.org/W2242005248","https://openalex.org/W2293049663","https://openalex.org/W2294038178","https://openalex.org/W2294351487","https://openalex.org/W2395578248","https://openalex.org/W2398524192","https://openalex.org/W2401544731","https://openalex.org/W2577042574","https://openalex.org/W2605320104","https://openalex.org/W2613407020","https://openalex.org/W4235154690"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2038801705","https://openalex.org/W2160650576","https://openalex.org/W2389184397","https://openalex.org/W2688184458","https://openalex.org/W2904846757","https://openalex.org/W175280642"],"abstract_inverted_index":{"This":[0,38,80],"paper":[1,39],"presents":[2],"a":[3,141],"novel":[4],"statistical":[5,61],"sample-based":[6,62],"approach":[7],"for":[8,69,125],"Gaussian":[9],"Mixture":[10],"Model":[11,75],"(GMM)-based":[12],"Voice":[13],"Conversion":[14],"(VC).":[15],"Although":[16],"GMM-based":[17,116,183,199],"VC":[18],"has":[19],"the":[20,41,50,54,104,166,177,197,206],"promising":[21],"flexibility":[22,102,195],"of":[23,35,43,49,103,181,196,214],"model":[24],"adaptation,":[25],"quality":[26,55,216],"in":[27,212,220],"converted":[28,221],"speech":[29,63,90,128,157,171,192,215],"is":[30,47,153,176],"significantly":[31],"worse":[32],"than":[33],"that":[34,180,205],"natural":[36],"speech.":[37,222],"addresses":[40],"problem":[42],"inaccurate":[44],"modeling,":[45],"which":[46],"one":[48],"main":[51],"reasons":[52],"causing":[53],"degradation.":[56],"Recently,":[57],"we":[58,111,133],"have":[59],"proposed":[60,167,207],"synthesis":[64],"using":[65,151,161],"rich":[66,119],"context":[67,120],"models":[68,121],"high-quality":[70,89,191],"and":[71,131,173,217],"flexible":[72],"Hidden":[73],"Markov":[74],"(HMM)-based":[76],"Text-To-Speech":[77],"(TTS)":[78],"synthesis.":[79],"method":[81,168,208],"makes":[82,186],"it":[83,185,187],"possible":[84,188],"not":[85],"only":[86],"to":[87,100,115,139,155,189],"produce":[88,190],"by":[91,137],"introducing":[92],"ideas":[93],"from":[94],"unit":[95],"selection":[96],"synthesis,":[97],"but":[98],"also":[99],"preserve":[101],"original":[105,198],"HMM-based":[106],"TTS.":[107],"In":[108,145],"this":[109,113],"paper,":[110],"apply":[112],"idea":[114],"VC.":[117,200],"The":[118,201],"are":[122],"first":[123],"trained":[124],"individual":[126,170],"joint":[127],"feature":[129],"vectors,":[130],"then":[132],"gather":[134],"them":[135],"mixture":[136,138],"form":[140],"Rich":[142],"context-GMM":[143],"(R-GMM).":[144],"conversion,":[146],"an":[147],"iterative":[148],"generation":[149],"algorithm":[150],"R-GMMs":[152],"used":[154],"convert":[156],"parameters,":[158],"after":[159],"initialization":[160],"over-trained":[162],"probability":[163],"distributions.":[164],"Because":[165],"utilizes":[169],"features,":[172],"its":[174],"formulation":[175],"same":[178],"as":[179],"conventional":[182],"VC,":[184],"while":[193],"keeping":[194],"experimental":[202],"results":[203],"demonstrate":[204],"yields":[209],"significant":[210],"improvements":[211],"term":[213],"speaker":[218],"individuality":[219]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}