{"id":"https://openalex.org/W2946856121","doi":"https://doi.org/10.1587/transinf.2018edl8264","title":"Prosody Correction Preserving Speaker Individuality for Chinese-Accented Japanese HMM-Based Text-to-Speech Synthesis","display_name":"Prosody Correction Preserving Speaker Individuality for Chinese-Accented Japanese HMM-Based Text-to-Speech Synthesis","publication_year":2019,"publication_date":"2019-05-31","ids":{"openalex":"https://openalex.org/W2946856121","doi":"https://doi.org/10.1587/transinf.2018edl8264","mag":"2946856121"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2018edl8264","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2018edl8264","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E102.D/6/E102.D_2018EDL8264/_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/E102.D/6/E102.D_2018EDL8264/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056339558","display_name":"Daiki Sekizawa","orcid":"https://orcid.org/0009-0004-0196-2612"},"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":true,"raw_author_name":"Daiki SEKIZAWA","raw_affiliation_strings":["University of Tokyo"],"affiliations":[{"raw_affiliation_string":"University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"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":["University of Tokyo"],"affiliations":[{"raw_affiliation_string":"University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"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":"Hiroshi SARUWATARI","raw_affiliation_strings":["University of Tokyo"],"affiliations":[{"raw_affiliation_string":"University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056339558"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04608206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"E102.D","issue":"6","first_page":"1218","last_page":"1221"},"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":0.9962000250816345,"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":0.9909999966621399,"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":0.9712265729904175},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8646608591079712},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.857520580291748},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.8025190830230713},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7115730047225952},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7107902765274048},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.4787289798259735},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.47249141335487366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3905373811721802},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.3392890691757202},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3290669918060303},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10518914461135864},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0612453818321228}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9712265729904175},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8646608591079712},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.857520580291748},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.8025190830230713},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7115730047225952},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7107902765274048},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.4787289798259735},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.47249141335487366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3905373811721802},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3392890691757202},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3290669918060303},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10518914461135864},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0612453818321228},{"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:10.1587/transinf.2018edl8264","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2018edl8264","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E102.D/6/E102.D_2018EDL8264/_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.2018edl8264","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2018edl8264","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E102.D/6/E102.D_2018EDL8264/_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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2946856121.pdf","grobid_xml":"https://content.openalex.org/works/W2946856121.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1523372075","https://openalex.org/W2000513720","https://openalex.org/W2005768155","https://openalex.org/W2049686551","https://openalex.org/W2102003408","https://openalex.org/W2111284386","https://openalex.org/W2120605154","https://openalex.org/W2153914468","https://openalex.org/W2395578248","https://openalex.org/W2559039559","https://openalex.org/W2765486990","https://openalex.org/W2963609956","https://openalex.org/W4395958265"],"related_works":["https://openalex.org/W3149582125","https://openalex.org/W2349468610","https://openalex.org/W2946856121","https://openalex.org/W2465421051","https://openalex.org/W1914543332","https://openalex.org/W2161314515","https://openalex.org/W2370805772","https://openalex.org/W2181715843","https://openalex.org/W652196294","https://openalex.org/W2395605663"],"abstract_inverted_index":{"This":[0],"article":[1],"proposes":[2],"a":[3],"prosody":[4],"correction":[5,87],"method":[6],"based":[7],"on":[8],"partial":[9],"model":[10,17],"adaptation":[11],"for":[12,91],"Chinese-accented":[13,59],"Japanese":[14,60,70],"hidden":[15],"Markov":[16],"(HMM)-based":[18],"text-to-speech":[19,22,61],"synthesis.":[20],"Although":[21],"synthesis":[23],"built":[24],"from":[25],"non-native":[26],"speech":[27,41,71],"accurately":[28],"reproduces":[29],"the":[30,36,39,46,51,55],"speaker's":[31],"individuality":[32,57],"in":[33],"synthetic":[34,40,75],"speech,":[35],"naturalness":[37,52],"of":[38,58,68,78],"is":[42],"strongly":[43],"degraded.":[44],"In":[45],"proposed":[47],"model,":[48],"to":[49,72],"improve":[50],"while":[53],"preserving":[54],"speaker":[56],"synthesis,":[62],"we":[63],"partially":[64],"utilize":[65],"HMM":[66],"parameters":[67],"native":[69],"synthesize":[73],"prosody-corrected":[74],"speech.":[76],"Results":[77],"an":[79],"experimental":[80],"evaluation":[81],"demonstrate":[82],"that":[83],"duration":[84],"and":[85],"F0":[86],"are":[88],"significantly":[89],"effective":[90],"improving":[92],"naturalness.":[93]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}