{"id":"https://openalex.org/W2395237272","doi":"https://doi.org/10.21437/interspeech.2015-121","title":"Non-native speech synthesis preserving speaker individuality based on partial correction of prosodic and phonetic characteristics","display_name":"Non-native speech synthesis preserving speaker individuality based on partial correction of prosodic and phonetic characteristics","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2395237272","doi":"https://doi.org/10.21437/interspeech.2015-121","mag":"2395237272"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-121","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-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/A5027457499","display_name":"Yuji Oshima","orcid":"https://orcid.org/0000-0001-6284-977X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuji Oshima","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000692949","display_name":"Graham Neubig","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":[],"affiliations":[]},{"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 & Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science & Technology#TAB#","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5027457499"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4314,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78824005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"299","last_page":"303"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9944000244140625,"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":0.9943000078201294,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.9258795380592346},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7585844993591309},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7322428226470947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7066742181777954},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5901592969894409},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5873528718948364},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.5122596621513367},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.47897103428840637},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4640447497367859},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4329458475112915},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2660245895385742}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9258795380592346},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7585844993591309},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7322428226470947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7066742181777954},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5901592969894409},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5873528718948364},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.5122596621513367},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.47897103428840637},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4640447497367859},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4329458475112915},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2660245895385742},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-121","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W113498433","https://openalex.org/W145536283","https://openalex.org/W172394764","https://openalex.org/W1503536879","https://openalex.org/W1523372075","https://openalex.org/W1590424750","https://openalex.org/W1597726554","https://openalex.org/W1600722501","https://openalex.org/W1967545654","https://openalex.org/W1984905644","https://openalex.org/W1991682319","https://openalex.org/W2007062874","https://openalex.org/W2009226274","https://openalex.org/W2049686551","https://openalex.org/W2106792148","https://openalex.org/W2111284386","https://openalex.org/W2117418893","https://openalex.org/W2120605154","https://openalex.org/W2123140629","https://openalex.org/W2123808477","https://openalex.org/W2152974894","https://openalex.org/W2154920538","https://openalex.org/W2242005248","https://openalex.org/W2395578248","https://openalex.org/W2396591423","https://openalex.org/W2405704522","https://openalex.org/W3177989406"],"related_works":["https://openalex.org/W2559039559","https://openalex.org/W2000164896","https://openalex.org/W2579204149","https://openalex.org/W2401456508","https://openalex.org/W2465347338","https://openalex.org/W1037880200","https://openalex.org/W2610641896","https://openalex.org/W2955237921","https://openalex.org/W3095859866","https://openalex.org/W2921333959","https://openalex.org/W2129042887","https://openalex.org/W2928664166","https://openalex.org/W1602171322","https://openalex.org/W2094999616","https://openalex.org/W1965770622","https://openalex.org/W1630928455","https://openalex.org/W90330241","https://openalex.org/W2023728986","https://openalex.org/W2005134222","https://openalex.org/W123930466"],"abstract_inverted_index":{"This":[0,69],"paper":[1,70],"presents":[2],"a":[3,14,34,56,72,151,161],"novel":[4],"non-native":[5,15,36,86],"speech":[6,18,26,32,48,63,67,77,87,98,118],"synthesis":[7,19,78],"technique":[8],"that":[9,79,176],"preserves":[10,80],"the":[11,39,45,90,94,104,108,117,132,136,188],"individuality":[12,60,82,106,190],"of":[13,33,58,96,135,182],"speaker.":[16,92],"Cross-lingual":[17],"based":[20,155,165],"on":[21,156,166],"voice":[22],"conversion":[23],"or":[24],"HMM-based":[25],"synthesis,":[27],"which":[28],"synthesizes":[29],"foreign":[30],"language":[31],"specific":[35],"speaker":[37,59,81,105,146,189],"reflecting":[38],"speaker-dependent":[40],"acoustic":[41],"characteristics":[42],"extracted":[43],"from":[44],"speaker\u2019s":[46],"natural":[47],"in":[49,61,107,131,191],"his/her":[50],"mother":[51],"tongue,":[52],"tends":[53],"to":[54,65,75,102],"cause":[55],"degradation":[57],"synthetic":[62,192],"compared":[64],"intra-lingual":[66],"synthesis.":[68],"proposes":[71],"new":[73],"approach":[74],"cross-lingual":[76],"by":[83,89,122,129],"explicitly":[84],"using":[85],"spoken":[88],"target":[91,110,139],"Although":[93],"use":[95],"nonnative":[97],"makes":[99],"it":[100],"possible":[101],"preserve":[103],"synthesized":[109],"speech,":[111],"naturalness":[112,143,185],"is":[113,119],"significantly":[114,183],"degraded":[115],"as":[116],"directly":[120],"affected":[121],"unnatural":[123],"prosody":[124],"and":[125,138,159],"pronunciation":[126],"often":[127],"caused":[128],"differences":[130],"linguistic":[133],"systems":[134],"source":[137],"languages.":[140],"To":[141],"improve":[142],"while":[144,186],"preserving":[145,187],"individuality,":[147],"we":[148],"propose":[149],"(1)":[150],"prosodic":[152],"correction":[153,163],"method":[154,164],"model":[157],"adaptation,":[158],"(2)":[160],"phonetic":[162],"spectrum":[167],"replacement":[168],"for":[169],"unvoiced":[170],"consonants.":[171],"The":[172],"experimental":[173],"results":[174],"demonstrate":[175],"these":[177],"proposed":[178],"methods":[179],"are":[180],"capable":[181],"improving":[184],"speech.":[193]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}