{"id":"https://openalex.org/W2898832121","doi":"https://doi.org/10.1109/taslp.2018.2878949","title":"Many-to-many and Completely Parallel-data-free Voice Conversion Based on Eigenspace DNN","display_name":"Many-to-many and Completely Parallel-data-free Voice Conversion Based on Eigenspace DNN","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2898832121","doi":"https://doi.org/10.1109/taslp.2018.2878949","mag":"2898832121"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2878949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2878949","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071170680","display_name":"T. Hashimoto","orcid":"https://orcid.org/0000-0001-7228-1428"},"institutions":[{"id":"https://openalex.org/I4210137853","display_name":"Toyota Motor Corporation (Japan)","ror":"https://ror.org/02zqm6r10","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4210137853"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Hashimoto","raw_affiliation_strings":["Toyota Motor Corporation, Aichi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Motor Corporation, Aichi, Japan","institution_ids":["https://openalex.org/I4210137853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["Graduate School of Engineering, University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010715755","display_name":"Daisuke Saito","orcid":"https://orcid.org/0000-0003-3012-1607"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Saito","raw_affiliation_strings":["Graduate School of Engineering, University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4742,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86883396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"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":0.9980000257492065,"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":0.9912999868392944,"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":0.8020896911621094},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5334119200706482},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5223559141159058},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49785399436950684},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4104347825050354},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41025295853614807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39656031131744385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8020896911621094},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5334119200706482},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5223559141159058},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49785399436950684},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4104347825050354},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41025295853614807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39656031131744385},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2878949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2878949","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2194958148","display_name":"Individual-based and automatic clustering of World Englishes and its application to assist international communication","funder_award_id":"26240022","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6546511184","display_name":"Development of L2 speech training infrastructure for objective measurement of speech comprehensibility based on native speakers' shadowing","funder_award_id":"18H04107","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W10800834","https://openalex.org/W49412823","https://openalex.org/W1588266896","https://openalex.org/W1665214252","https://openalex.org/W1904365287","https://openalex.org/W1950777589","https://openalex.org/W1965255698","https://openalex.org/W2005522781","https://openalex.org/W2009396100","https://openalex.org/W2015060114","https://openalex.org/W2049686551","https://openalex.org/W2123003832","https://openalex.org/W2126143605","https://openalex.org/W2150769028","https://openalex.org/W2156142001","https://openalex.org/W2161476805","https://openalex.org/W2404109308","https://openalex.org/W2574092538","https://openalex.org/W2576484574","https://openalex.org/W2748561347","https://openalex.org/W6600438624","https://openalex.org/W6602007935","https://openalex.org/W6635216677","https://openalex.org/W6637242042","https://openalex.org/W6640036494","https://openalex.org/W6713593013","https://openalex.org/W6743505753"],"related_works":["https://openalex.org/W1952261593","https://openalex.org/W2014494654","https://openalex.org/W1975321310","https://openalex.org/W2990323019","https://openalex.org/W3130349901","https://openalex.org/W1579833936","https://openalex.org/W2095350775","https://openalex.org/W1516392727","https://openalex.org/W1578916557","https://openalex.org/W2171745948"],"abstract_inverted_index":{"Media":[0],"conversion":[1,18,57,68,108,160,213],"of":[2,12,32,54,74,82,174,220,231,242,259,270,283],"image,":[3],"text,":[4],"speech,":[5],"etc.,":[6],"generally":[7],"requires":[8],"a":[9,17,29,71,88,102,158,228,284],"large":[10,72],"amount":[11,31,73],"parallel":[13,33,49,61,76,114,123,205,249,263,276,289],"data":[14,34,50,62,77,115,124,277],"for":[15,22,125],"training":[16,23,187],"model.":[19],"Recently,":[20],"methods":[21],"the":[24,56,83,164,196,200,232,240,271],"model":[25,90,104,161],"using":[26,195,274],"no":[27,60,262,275],"or":[28],"small":[30],"draw":[35],"researchers'":[36],"attention.":[37],"In":[38,128],"many-to-many":[39,66,138,159],"voice":[40,67,139],"conversion,":[41],"since":[42],"it":[43,179],"is":[44,157,180,254],"often":[45],"hard":[46],"to":[47,78,95,185,211,255,281],"collect":[48],"from":[51,91],"every":[52],"pair":[53],"speakers,":[55],"models":[58,69,109,149,177],"requiring":[59],"are":[63,209,278],"desired.":[64],"Conventional":[65],"required":[70],"prestored":[75],"acquire":[79],"prior":[80,126],"knowledge":[81],"entire":[84,165],"speaker":[85,94,166,197,223],"space.":[86],"Then,":[87],"specific":[89],"an":[92,117],"arbitrary":[93],"another":[96],"can":[97,224],"be":[98,225,236],"realized":[99],"by":[100,170,227],"adapting":[101],"few":[103],"parameters.":[105],"Although":[106],"these":[107,217],"certainly":[110],"do":[111,245],"not":[112,246],"use":[113,122],"in":[116,182],"adaptation":[118],"step,":[119],"they":[120],"still":[121],"training.":[127],"this":[129],"study,":[130],"we":[131],"aim":[132],"at":[133],"realizing":[134],"completely":[135],"parallel-data-free":[136],"and":[137,151,178,199],"conversion.":[140],"The":[141],"proposed":[142,272],"method":[143,184,273],"uses":[144],"both":[145],"Eigenvoice":[146],"Gaussian":[147,175],"mixture":[148,176],"(EVGMM)":[150],"Deep":[152],"neural":[153],"network":[154],"(DNN).":[155],"EVGMM":[156,260],"that":[162,238,267],"constructs":[163],"space":[167],"(called":[168],"eigenspace)":[169],"analyzing":[171],"mean":[172],"vectors":[173],"used":[181],"our":[183,243],"decompose":[186],"speakers'":[188],"features":[189,198,219],"into":[190],"their":[191],"eigenspace":[192],"components.":[193,233],"By":[194],"obtained":[201],"components":[202],"as":[203],"pseudo":[204],"data,":[206],"multiple":[207],"DNNs":[208],"trained":[210,287],"realize":[212],"between":[214],"them.":[215],"With":[216],"DNNs,":[218],"any":[221,248],"target":[222],"represented":[226],"weighted":[229],"sum":[230],"It":[234],"should":[235],"noted":[237],"all":[239],"processes":[241],"proposal":[244],"require":[247],"data.":[250,264,290],"A":[251],"key":[252],"technique":[253],"estimate":[256],"covariance":[257],"terms":[258],"with":[261,288],"Experiments":[265],"indicate":[266],"individuality":[268],"scores":[269],"comparable":[279],"enough":[280],"those":[282],"baseline":[285],"system":[286]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}