{"id":"https://openalex.org/W2787685498","doi":"https://doi.org/10.1587/transinf.2017edp7165","title":"DNN-Based Speech Synthesis Using Speaker Codes","display_name":"DNN-Based Speech Synthesis Using Speaker Codes","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2787685498","doi":"https://doi.org/10.1587/transinf.2017edp7165","mag":"2787685498"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2017edp7165","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edp7165","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E101.D/2/E101.D_2017EDP7165/_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/E101.D/2/E101.D_2017EDP7165/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079710814","display_name":"Nobukatsu Hojo","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobukatsu HOJO","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068604686","display_name":"Yusuke Ijima","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke IJIMA","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102842694","display_name":"Hideyuki Mizuno","orcid":"https://orcid.org/0000-0002-2591-7152"},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideyuki MIZUNO","raw_affiliation_strings":["Tokyo University of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo University of Science","institution_ids":["https://openalex.org/I161296585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7445,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.9672722,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"E101.D","issue":"2","first_page":"462","last_page":"472"},"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/T11309","display_name":"Music and Audio Processing","score":0.9927999973297119,"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/T10860","display_name":"Speech and Audio Processing","score":0.9915000200271606,"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":0.8391454219818115},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7823218107223511},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5830204486846924},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5395431518554688},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5371246337890625},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4826357960700989},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.478437215089798},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.441410094499588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3563987612724304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8391454219818115},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7823218107223511},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5830204486846924},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5395431518554688},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5371246337890625},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4826357960700989},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.478437215089798},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.441410094499588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3563987612724304}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2017edp7165","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edp7165","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E101.D/2/E101.D_2017EDP7165/_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.2017edp7165","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edp7165","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E101.D/2/E101.D_2017EDP7165/_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":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2787685498.pdf","grobid_xml":"https://content.openalex.org/works/W2787685498.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W102093577","https://openalex.org/W1492383498","https://openalex.org/W1522301498","https://openalex.org/W1570874634","https://openalex.org/W1892788530","https://openalex.org/W1984905644","https://openalex.org/W1990505856","https://openalex.org/W1993409002","https://openalex.org/W2000513720","https://openalex.org/W2049686551","https://openalex.org/W2079623482","https://openalex.org/W2102003408","https://openalex.org/W2112021726","https://openalex.org/W2153914468","https://openalex.org/W2154920538","https://openalex.org/W2269105564","https://openalex.org/W2294797155","https://openalex.org/W2400136144","https://openalex.org/W2401698713","https://openalex.org/W2516321201","https://openalex.org/W2605320104","https://openalex.org/W2759925408","https://openalex.org/W4235154690"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2038801705","https://openalex.org/W2688184458","https://openalex.org/W2162158162","https://openalex.org/W2904846757","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"(DNN)-based":[3],"speech":[4,11,16,26,35,45,102,131],"synthesis":[5,46,103],"can":[6,28],"produce":[7],"more":[8],"natural":[9],"synthesized":[10,25],"than":[12],"the":[13,24,55,58,71,73,81,85,91,113,117,125,137,142,149,153,166,180,183,189,199,225,230],"conventional":[14,59,86,203,231],"HMM-based":[15],"synthesis.":[17],"However,":[18],"it":[19],"is":[20,78,146,169],"not":[21],"revealed":[22,197],"whether":[23],"quality":[27],"be":[29],"improved":[30],"by":[31],"utilizing":[32],"a":[33,51,129,160,173,214,240],"multi-speaker":[34,107,114,130,135,167,210],"corpus.":[36,132],"To":[37],"address":[38],"this":[39,41],"problem,":[40],"paper":[42,89],"proposes":[43],"DNN-based":[44,62],"using":[47,128,239],"speaker":[48,60,68,95,110,138,145,158,206,234,245],"codes":[49,96],"as":[50],"method":[52,118],"to":[53,66,80,97,141,148,151,171],"improve":[54],"performance":[56,185],"of":[57,84,93,124,162,165,188,243],"dependent":[61,207,235],"method.":[63],"In":[64],"order":[65],"model":[67,168,201,227],"variation":[69],"in":[70],"DNN,":[72],"augmented":[74],"feature":[75],"(speaker":[76],"codes)":[77],"fed":[79,147],"hidden":[82,216],"layer(s)":[83],"DNN.":[87],"This":[88],"investigates":[90],"effectiveness":[92],"introducing":[94],"DNN":[98,127,150],"acoustic":[99],"models":[100],"for":[101,104],"two":[105],"tasks:":[106],"modeling":[108,115],"and":[109,186,209],"adaptation.":[111],"For":[112],"task,":[116],"we":[119],"propose":[120],"trains":[121],"connection":[122,163],"weights":[123,164],"whole":[126],"When":[133,156],"performing":[134,157],"synthesis,":[136],"code":[139],"corresponding":[140],"selected":[143],"target":[144,175,244],"generate":[152,172],"speaker's":[154,176],"voice.":[155,177],"adaptation,":[159],"set":[161],"re-estimated":[170],"new":[174],"We":[178],"investigated":[179],"relationship":[181],"between":[182],"prediction":[184],"architecture":[187],"DNNs":[190,208,211],"through":[191],"objective":[192],"measurements.":[193],"Objective":[194],"evaluation":[195,220],"experiments":[196],"that":[198,224],"proposed":[200,226],"outperformed":[202,229],"methods":[204,232],"(HMMs,":[205,233],"based":[212],"on":[213],"shared":[215],"layer":[217],"structure).":[218],"Subjective":[219],"experimental":[221],"results":[222],"showed":[223],"again":[228],"DNNs),":[236],"especially":[237],"when":[238],"small":[241],"number":[242],"utterances.":[246]},"counts_by_year":[{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}