{"id":"https://openalex.org/W2559039559","doi":"https://doi.org/10.1587/transinf.2016edp7231","title":"Non-Native Text-to-Speech Preserving Speaker Individuality Based on Partial Correction of Prosodic and Phonetic Characteristics","display_name":"Non-Native Text-to-Speech Preserving Speaker Individuality Based on Partial Correction of Prosodic and Phonetic Characteristics","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2559039559","doi":"https://doi.org/10.1587/transinf.2016edp7231","mag":"2559039559"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2016edp7231","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016edp7231","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/12/E99.D_2016EDP7231/_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/12/E99.D_2016EDP7231/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027457499","display_name":"Yuji Oshima","orcid":"https://orcid.org/0000-0001-6284-977X"},"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":"Yuji OSHIMA","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology"],"raw_orcid":null,"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/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"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":"Shinnosuke TAKAMICHI","raw_affiliation_strings":["Department of Information Physics and Computing, Graduate School of Information Science and Technology, The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Physics and Computing, Graduate School of Information Science and Technology, The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"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"]},{"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":"Tomoki TODA","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology","Information Technology Center, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]},{"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"],"raw_orcid":null,"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"],"raw_orcid":null,"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"],"raw_orcid":null,"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":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2993,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87571236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"E99.D","issue":"12","first_page":"3132","last_page":"3139"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9943000078201294,"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/T12031","display_name":"Speech and dialogue systems","score":0.9902999997138977,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8848493099212646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7758302688598633},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7241082787513733},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7218334078788757},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6836596131324768},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.661238968372345},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5566737651824951},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.48467186093330383},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.4230841398239136},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4121738076210022},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22210043668746948}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8848493099212646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7758302688598633},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7241082787513733},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7218334078788757},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6836596131324768},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.661238968372345},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5566737651824951},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.48467186093330383},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.4230841398239136},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4121738076210022},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22210043668746948},{"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},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2016edp7231","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016edp7231","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/12/E99.D_2016EDP7231/_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.2016edp7231","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016edp7231","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/12/E99.D_2016EDP7231/_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":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"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"}],"funders":[{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320335839","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2559039559.pdf","grobid_xml":"https://content.openalex.org/works/W2559039559.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W59075858","https://openalex.org/W113498433","https://openalex.org/W145536283","https://openalex.org/W172394764","https://openalex.org/W1503536879","https://openalex.org/W1523372075","https://openalex.org/W1535240601","https://openalex.org/W1590424750","https://openalex.org/W1597726554","https://openalex.org/W1600722501","https://openalex.org/W1635512741","https://openalex.org/W1966136862","https://openalex.org/W1967545654","https://openalex.org/W1984905644","https://openalex.org/W1990505856","https://openalex.org/W1991682319","https://openalex.org/W2005768155","https://openalex.org/W2007062874","https://openalex.org/W2049686551","https://openalex.org/W2084609288","https://openalex.org/W2098380781","https://openalex.org/W2106792148","https://openalex.org/W2109444541","https://openalex.org/W2111284386","https://openalex.org/W2114010348","https://openalex.org/W2117418893","https://openalex.org/W2120605154","https://openalex.org/W2123808477","https://openalex.org/W2129142580","https://openalex.org/W2152974894","https://openalex.org/W2153914468","https://openalex.org/W2154920538","https://openalex.org/W2242005248","https://openalex.org/W2293049663","https://openalex.org/W2395237272","https://openalex.org/W2395578248","https://openalex.org/W2396591423","https://openalex.org/W2405704522","https://openalex.org/W2619993508","https://openalex.org/W3177989406"],"related_works":["https://openalex.org/W1564152904","https://openalex.org/W2968379855","https://openalex.org/W2110108310","https://openalex.org/W2904846757","https://openalex.org/W3016950637","https://openalex.org/W2782856092","https://openalex.org/W2579204149","https://openalex.org/W2181773877","https://openalex.org/W2225513120","https://openalex.org/W2559039559"],"abstract_inverted_index":{"This":[0,79],"paper":[1,80],"presents":[2],"a":[3,14,32,40,57,82,161,171,224],"novel":[4],"non-native":[5,15,94,105],"speech":[6,18,29,38,44,73,77,86,95,106,127,187],"synthesis":[7,19,30,87],"technique":[8,33,52],"that":[9,88,194],"preserves":[10,89],"the":[11,51,98,102,112,116,125,142,146,196,207,215],"individuality":[12,70,91,114,209],"of":[13,60,67,104,145,201],"speaker.":[16,100],"Cross-lingual":[17],"based":[20,165,175],"on":[21,166,176],"voice":[22],"conversion":[23],"or":[24],"Hidden":[25],"Markov":[26],"Model":[27],"(HMM)-based":[28],"is":[31,121,129],"to":[34,55,64,75,85,110],"synthesize":[35],"foreign":[36],"language":[37],"using":[39,93,185],"target":[41,68,99,118,149],"speaker's":[42,69],"natural":[43],"uttered":[45,188],"in":[46,71,115,141,210],"his/her":[47],"mother":[48],"tongue.":[49],"Although":[50,101],"holds":[53],"promise":[54],"improve":[56,152,219],"wide":[58],"variety":[59],"applications,":[61],"it":[62,108],"tends":[63],"cause":[65],"degradation":[66],"synthetic":[72,211],"compared":[74],"intra-lingual":[76],"synthesis.":[78],"proposes":[81],"new":[83],"approach":[84],"speaker":[90,113,156,208],"by":[92,97,132,139,189,223],"spoken":[96],"use":[103],"makes":[107],"possible":[109],"preserve":[111],"synthesized":[117,126],"speech,":[119,212],"naturalness":[120,153,204],"significantly":[122,202],"degraded":[123],"as":[124,221],"waveform":[128],"directly":[130],"affected":[131],"unnatural":[133],"prosody":[134,162],"and":[135,148,169,213],"pronunciation":[136],"often":[137],"caused":[138],"differences":[140],"linguistic":[143],"systems":[144],"source":[147],"languages.":[150],"To":[151],"while":[154,205],"preserving":[155,206],"individuality,":[157],"we":[158],"propose":[159],"(1)":[160,195],"correction":[163,173],"method":[164,174],"model":[167],"adaptation,":[168],"(2)":[170,214],"phonetic":[172],"spectrum":[177],"replacement":[178],"for":[179],"unvoiced":[180],"consonants.":[181],"The":[182],"experimental":[183],"results":[184],"English":[186],"native":[190],"Japanese":[191],"speakers":[192],"demonstrate":[193],"proposed":[197,216],"methods":[198,217],"are":[199],"capable":[200],"improving":[203],"also":[218],"intelligibility":[220],"confirmed":[222],"dictation":[225],"test.":[226]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
