{"id":"https://openalex.org/W3095491807","doi":"https://doi.org/10.21437/interspeech.2020-2477","title":"Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis","display_name":"Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095491807","doi":"https://doi.org/10.21437/interspeech.2020-2477","mag":"3095491807"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2477","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","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/A5086910479","display_name":"Yukiya Hono","orcid":"https://orcid.org/0000-0003-1245-8791"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukiya Hono","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073482780","display_name":"Kazuna Tsuboi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuna Tsuboi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001979247","display_name":"Kei Sawada","orcid":"https://orcid.org/0009-0003-2396-681X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kei Sawada","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067594810","display_name":"Kei Hashimoto","orcid":"https://orcid.org/0000-0003-2081-0396"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kei Hashimoto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049909008","display_name":"Keiichiro Oura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keiichiro Oura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240652","display_name":"Yoshihiko Nankaku","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoshihiko Nankaku","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3441","last_page":"3445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.994700014591217,"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":0.994700014591217,"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":0.9592999815940857,"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/T10860","display_name":"Speech and Audio Processing","score":0.9409000277519226,"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/latent-variable","display_name":"Latent variable","score":0.8536036610603333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.728627622127533},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6280710697174072},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5389971733093262},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5217003226280212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4646674394607544},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4258999526500702},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38505756855010986},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3122369050979614},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12477585673332214}],"concepts":[{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.8536036610603333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.728627622127533},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6280710697174072},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5389971733093262},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5217003226280212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4646674394607544},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4258999526500702},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38505756855010986},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3122369050979614},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12477585673332214},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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:10.21437/interspeech.2020-2477","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2988134182","https://openalex.org/W4394785709","https://openalex.org/W4309969736","https://openalex.org/W2953501176","https://openalex.org/W2965095304","https://openalex.org/W2470043383","https://openalex.org/W3034474024","https://openalex.org/W2770818364","https://openalex.org/W4317242571","https://openalex.org/W2616125534"],"abstract_inverted_index":{"This":[0,94],"paper":[1],"proposes":[2],"a":[3,8,67,83,88,98,102,106],"hierarchical":[4,84],"generative":[5],"model":[6],"with":[7],"multi-grained":[9,99],"latent":[10,20,50,74,92,109,116,122,144],"variable":[11],"to":[12,111],"synthesize":[13],"expressive":[14],"speech.":[15,41],"In":[16],"recent":[17],"years,":[18],"fine-grained":[19,73,143],"variables":[21,51,117,123,145],"are":[22,52],"introduced":[23],"into":[24,130],"the":[25,30,34,43,57,72,77,113,120,125,132,147,151,159],"text-to-speech":[26],"synthesis":[27,152],"that":[28],"enable":[29],"fine":[31],"control":[32],"of":[33,39,45,91,97,141,161],"prosody":[35],"and":[36,87,105,118],"speaking":[37,162],"styles":[38],"synthesized":[40],"However,":[42],"naturalness":[44],"speech":[46],"degrades":[47],"when":[48],"these":[49],"obtained":[53],"by":[54,128],"sampling":[55,142],"from":[56,124],"standard":[58],"Gaussian":[59],"prior.":[60],"To":[61],"solve":[62],"this":[63],"problem,":[64],"we":[65],"propose":[66],"novel":[68],"framework":[69,95,156],"for":[70],"modeling":[71],"variables,":[75],"considering":[76],"dependence":[78],"on":[79],"an":[80,138,165],"input":[81,133],"text,":[82],"linguistic":[85],"structure,":[86],"temporal":[89],"structure":[90],"variables.":[93],"consists":[96],"variational":[100],"autoencoder,":[101],"conditional":[103],"prior,":[104],"multi-level":[107],"auto-regressive":[108],"converter":[110],"obtain":[112],"different":[114],"time-resolution":[115],"sample":[119],"finer-level":[121],"coarser-level":[126],"ones":[127],"taking":[129],"account":[131],"text.":[134],"Experimental":[135],"results":[136],"indicate":[137],"appropriate":[139],"method":[140],"without":[146],"reference":[148],"signal":[149],"at":[150],"stage.":[153],"Our":[154],"proposed":[155],"also":[157],"provides":[158],"controllability":[160],"style":[163],"in":[164],"entire":[166],"utterance.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}