{"id":"https://openalex.org/W4206003764","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660456","title":"Using Local Phrase Dependency Structure Information in Neural Sequence-to-Sequence Speech Synthesis","display_name":"Using Local Phrase Dependency Structure Information in Neural Sequence-to-Sequence Speech Synthesis","publication_year":2021,"publication_date":"2021-11-18","ids":{"openalex":"https://openalex.org/W4206003764","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660456"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda202152914.2021.9660456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5016392060","display_name":"Nobuyoshi Kaiki","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":true,"raw_author_name":"Nobuyoshi Kaiki","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","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"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan","RIKEN AIP, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN AIP, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"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/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"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 and Technology, Japan","RIKEN AIP, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN AIP, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016392060"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65241978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"206","last_page":"211"},"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":0.9994999766349792,"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":0.9973999857902527,"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/prosody","display_name":"Prosody","score":0.7945852279663086},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7839860320091248},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7395032644271851},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.6836773157119751},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6490784883499146},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.641087532043457},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6328971982002258},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.605494499206543},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5951635241508484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5679318904876709},{"id":"https://openalex.org/keywords/dependency-grammar","display_name":"Dependency grammar","score":0.525432288646698},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.5136317610740662},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5028998255729675},{"id":"https://openalex.org/keywords/phrase-structure-rules","display_name":"Phrase structure rules","score":0.42103493213653564},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.41574132442474365},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2251303493976593}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7945852279663086},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7839860320091248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7395032644271851},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6836773157119751},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6490784883499146},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.641087532043457},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6328971982002258},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.605494499206543},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5951635241508484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5679318904876709},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.525432288646698},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.5136317610740662},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5028998255729675},{"id":"https://openalex.org/C80877019","wikidata":"https://www.wikidata.org/wiki/Q7188074","display_name":"Phrase structure rules","level":3,"score":0.42103493213653564},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.41574132442474365},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2251303493976593},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda202152914.2021.9660456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2962780374","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972831865","https://openalex.org/W3015338123","https://openalex.org/W3128170746"],"related_works":["https://openalex.org/W4253134045","https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3186487487","https://openalex.org/W3149582125","https://openalex.org/W2474947928","https://openalex.org/W1984347656","https://openalex.org/W4245842791","https://openalex.org/W157238252","https://openalex.org/W1489682032"],"abstract_inverted_index":{"We":[0,26],"introduce":[1],"end-to-end":[2,152],"text-to-speech":[3],"synthesis":[4],"(TTS)":[5],"with":[6,23,33,48,123],"prosodic":[7,34,49],"symbols":[8,35,50],"that":[9,51,78,120],"represent":[10],"phrase":[11,43,58,81,139],"components":[12,61],"based":[13,62],"on":[14,63],"local":[15,138],"syntactic":[16,38],"dependency":[17,39,140],"structures":[18],"for":[19],"synthesizing":[20],"Japanese":[21,151],"speech":[22,122],"natural":[24,124],"prosody.":[25],"propose":[27],"two":[28,71,97],"TTS":[29],"models:":[30],"1)":[31,75],"one":[32],"representing":[36],"the":[37,42,57,80,88,93,101,128,132,137,145],"distance":[40],"at":[41,87],"boundaries":[44],"and":[45,59,83,144],"2)":[46,84],"another":[47],"reflect":[52],"a":[53,114,150],"superimposed":[54],"model":[55,103,148],"of":[56,95,142],"accent":[60,106],"an":[64,110],"F0":[65,85,146],"generation":[66,147],"control":[67],"mechanism.":[68],"Using":[69],"these":[70,96],"models,":[72],"we":[73,108],"observed":[74],"pause":[76],"insertion":[77],"indicates":[79],"boundary":[82],"resetting":[86],"right-branching":[89],"boundaries.":[90],"To":[91],"verify":[92],"effectiveness":[94],"proposed":[98],"models":[99],"against":[100],"conventional":[102],"using":[104,136],"only":[105],"components,":[107],"conducted":[109],"AB":[111],"test":[112],"as":[113],"subjective":[115],"evaluation.":[116],"Our":[117],"result":[118],"confirmed":[119],"synthetic":[121],"prosody,":[125],"which":[126],"reflects":[127],"corresponding":[129],"intention":[130],"to":[131],"utterance,":[133],"was":[134],"generated":[135],"information":[141],"sentences":[143],"in":[149],"TTS.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}