{"id":"https://openalex.org/W2525520955","doi":"https://doi.org/10.1587/transinf.2016slp0011","title":"Investigation of Using Continuous Representation of Various Linguistic Units in Neural Network Based Text-to-Speech Synthesis","display_name":"Investigation of Using Continuous Representation of Various Linguistic Units in Neural Network Based Text-to-Speech Synthesis","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2525520955","doi":"https://doi.org/10.1587/transinf.2016slp0011","mag":"2525520955"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2016slp0011","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016slp0011","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0011/_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/10/E99.D_2016SLP0011/_pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]},{"id":"https://openalex.org/I4210110163","display_name":"Nippon Soken (Japan)","ror":"https://ror.org/01yk36x23","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210110163"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin WANG","raw_affiliation_strings":["National Institute of Informatics","SOKENDAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"SOKENDAI","institution_ids":["https://openalex.org/I200475212","https://openalex.org/I4210110163"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji TAKAKI","raw_affiliation_strings":["National Institute of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]},{"id":"https://openalex.org/I4210110163","display_name":"Nippon Soken (Japan)","ror":"https://ror.org/01yk36x23","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210110163"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Junichi YAMAGISHI","raw_affiliation_strings":["Centre for Speech Technology Research (CSTR), University of Edinburgh","National Institute of Informatics","SOKENDAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"SOKENDAI","institution_ids":["https://openalex.org/I200475212","https://openalex.org/I4210110163"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6459,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90157857,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"E99.D","issue":"10","first_page":"2471","last_page":"2480"},"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":0.9987000226974487,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8596828579902649},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6283642053604126},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5879627466201782},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5839799642562866},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5782588720321655},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5777919888496399},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5480879545211792},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5140775442123413},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5047637224197388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4997110366821289},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.42283302545547485},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12582385540008545}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8596828579902649},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6283642053604126},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5879627466201782},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5839799642562866},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5782588720321655},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5777919888496399},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5480879545211792},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5140775442123413},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5047637224197388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4997110366821289},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.42283302545547485},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12582385540008545},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1587/transinf.2016slp0011","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016slp0011","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0011/_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"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/71ec30e2-1fee-4a3a-957d-a4eeb9c2f0d9","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/71ec30e2-1fee-4a3a-957d-a4eeb9c2f0d9","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Wang, X, Takaki, S & Yamagishi, J 2016, 'Investigation of Using Continuous Representation of Various Linguistic Units in Neural Network Based Text-to-Speech Synthesis', IEICE Transactions on Information and Systems, vol. E99.D, no. 10, pp. 2471-2480. https://doi.org/10.1587/transinf.2016SLP0011","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.ed.ac.uk:publications/71ec30e2-1fee-4a3a-957d-a4eeb9c2f0d9","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/71ec30e2-1fee-4a3a-957d-a4eeb9c2f0d9","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.1587/transinf.2016slp0011","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016slp0011","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0011/_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":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2521286739","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G3007105200","display_name":"Deep architectures for statistical speech synthesis","funder_award_id":"EP/J002526/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3016163246","display_name":null,"funder_award_id":"26540092","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G3335014390","display_name":null,"funder_award_id":"15K12071","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G3349790956","display_name":"Direct modeling of speech waveform using a DNN for text-to-speech synthesis","funder_award_id":"16K16096","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3790594077","display_name":"Natural Speech Technology","funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6082203376","display_name":null,"funder_award_id":"EP/J002526/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6280338533","display_name":null,"funder_award_id":"15H01686","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G7705992122","display_name":null,"funder_award_id":"26280066","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G7879866177","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G8991044360","display_name":null,"funder_award_id":"16K16096","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320325763","display_name":"Telecommunications Advancement Foundation","ror":"https://ror.org/05y77zf79"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2525520955.pdf","grobid_xml":"https://content.openalex.org/works/W2525520955.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W68293321","https://openalex.org/W120415783","https://openalex.org/W162654330","https://openalex.org/W1537929847","https://openalex.org/W1570629387","https://openalex.org/W1578102511","https://openalex.org/W1615991656","https://openalex.org/W1632114991","https://openalex.org/W1779680350","https://openalex.org/W2019413183","https://openalex.org/W2049686551","https://openalex.org/W2092654472","https://openalex.org/W2093476462","https://openalex.org/W2099062766","https://openalex.org/W2100796029","https://openalex.org/W2102003408","https://openalex.org/W2108783283","https://openalex.org/W2111284386","https://openalex.org/W2123409957","https://openalex.org/W2125076245","https://openalex.org/W2131744502","https://openalex.org/W2141599568","https://openalex.org/W2144499799","https://openalex.org/W2150658333","https://openalex.org/W2153579005","https://openalex.org/W2158139315","https://openalex.org/W2158899491","https://openalex.org/W2276324605","https://openalex.org/W2402610474","https://openalex.org/W2485688913","https://openalex.org/W4205359331","https://openalex.org/W4231109964","https://openalex.org/W4390911407","https://openalex.org/W4390911804"],"related_works":["https://openalex.org/W4288407670","https://openalex.org/W2950396480","https://openalex.org/W947140380","https://openalex.org/W2911655849","https://openalex.org/W4286432911","https://openalex.org/W4230884544","https://openalex.org/W4245453790","https://openalex.org/W3194985222","https://openalex.org/W3216571906","https://openalex.org/W4214830338"],"abstract_inverted_index":{"Building":[0],"high-quality":[1],"text-to-speech":[2],"(TTS)":[3],"systems":[4],"without":[5],"expert":[6],"knowledge":[7],"of":[8,16,31,40,56,102,125,131,157,170],"the":[9,41,53,79,100,113,118,126,138,146,158,167,181,187,192],"target":[10],"language":[11,70],"and/or":[12],"time-consuming":[13],"manual":[14],"annotation":[15],"speech":[17],"and":[18,48,110,120],"text":[19,43],"data":[20],"is":[21,35,45,178],"an":[22],"important":[23],"yet":[24],"challenging":[25],"research":[26],"topic.":[27],"In":[28,94],"this":[29,95,103],"kind":[30],"TTS":[32,92],"system,":[33],"it":[34,177],"vital":[36],"to":[37,50,86,106,186],"find":[38],"representation":[39,55,169],"input":[42,84,185],"that":[44,129,166],"both":[46],"effective":[47],"easy":[49],"acquire.":[51],"Recently,":[52],"continuous":[54,133,168],"raw":[57],"word":[58],"inputs,":[59],"called":[60],"\u201cword":[61],"embedding\u201d,":[62],"has":[63,74],"been":[64,76],"successfully":[65],"used":[66,77],"in":[67],"various":[68],"natural":[69],"processing":[71],"tasks.":[72],"It":[73],"also":[75],"as":[78,150,154,184],"additional":[80,151],"or":[81,153],"alternative":[82],"linguistic":[83],"features":[85],"a":[87,155],"neural-network-based":[88],"acoustic":[89,114,147,188],"model":[90,115,148,189],"for":[91,112],"systems.":[93],"paper,":[96],"we":[97],"further":[98],"investigate":[99],"use":[101],"embedding":[104],"technique":[105],"represent":[107],"phonemes,":[108],"syllables":[109],"phrases":[111,171],"based":[116,190],"on":[117,191],"recurrent":[119],"feed-forward":[121,193],"neural":[122,194],"network.":[123,195],"Results":[124],"experiments":[127],"show":[128],"most":[130],"these":[132],"representations":[134],"cannot":[135],"significantly":[136],"improve":[137],"system's":[139],"performance":[140],"when":[141,176],"they":[142],"are":[143],"fed":[144],"into":[145],"either":[149],"component":[152],"replacement":[156],"conventional":[159],"prosodic":[160,182],"context.":[161],"However,":[162],"subjective":[163],"evaluation":[164],"shows":[165],"can":[172],"achieve":[173],"significant":[174],"improvement":[175],"combined":[179],"with":[180],"context":[183]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}