{"id":"https://openalex.org/W2745387029","doi":"https://doi.org/10.21437/interspeech.2017-628","title":"A Hierarchical Encoder-Decoder Model for Statistical Parametric Speech Synthesis","display_name":"A Hierarchical Encoder-Decoder Model for Statistical Parametric Speech Synthesis","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2745387029","doi":"https://doi.org/10.21437/interspeech.2017-628","mag":"2745387029"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-628","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/229103a7-2201-4815-a07c-04f5457e9a0a","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004616142","display_name":"Srikanth Ronanki","orcid":null},"institutions":[{"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"],"is_corresponding":true,"raw_author_name":"Srikanth Ronanki","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110238677","display_name":"Oliver Watts","orcid":null},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Oliver Watts","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004616142"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":1.5602,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.8734999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1133","last_page":"1137"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.7957291007041931},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6290630102157593},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5882196426391602},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5478236675262451},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5377820134162903},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.528988242149353},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.4884563982486725},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4654572308063507},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4275498390197754},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.41021350026130676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3474469482898712}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7957291007041931},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6290630102157593},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5882196426391602},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5478236675262451},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5377820134162903},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.528988242149353},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.4884563982486725},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4654572308063507},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4275498390197754},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.41021350026130676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3474469482898712},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-628","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/229103a7-2201-4815-a07c-04f5457e9a0a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/229103a7-2201-4815-a07c-04f5457e9a0a","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ronanki, S, Watts, O & King, S 2017, A Hierarchical Encoder-Decoder Model for Statistical Parametric Speech Synthesis. in Proceedings Interspeech 2017. pp. 1133-1137, Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-628","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/229103a7-2201-4815-a07c-04f5457e9a0a","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/229103a7-2201-4815-a07c-04f5457e9a0a","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":"pmh:oai:pure.ed.ac.uk:openaire/229103a7-2201-4815-a07c-04f5457e9a0a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/229103a7-2201-4815-a07c-04f5457e9a0a","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ronanki, S, Watts, O & King, S 2017, A Hierarchical Encoder-Decoder Model for Statistical Parametric Speech Synthesis. in Proceedings Interspeech 2017. pp. 1133-1137, Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-628","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7898478334","display_name":null,"funder_award_id":"EP/P011586/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1499332833","https://openalex.org/W1576227399","https://openalex.org/W1578102511","https://openalex.org/W1783473872","https://openalex.org/W1815076433","https://openalex.org/W1828163288","https://openalex.org/W2102003408","https://openalex.org/W2129142580","https://openalex.org/W2130942839","https://openalex.org/W2134973740","https://openalex.org/W2150612204","https://openalex.org/W2152205330","https://openalex.org/W2154920538","https://openalex.org/W2157331557","https://openalex.org/W2158139315","https://openalex.org/W2184310502","https://openalex.org/W2250539671","https://openalex.org/W2294797155","https://openalex.org/W2327501763","https://openalex.org/W2394662942","https://openalex.org/W2400063444","https://openalex.org/W2513051195","https://openalex.org/W2513112113","https://openalex.org/W2515943672","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2598638573","https://openalex.org/W2964060510","https://openalex.org/W2964301388","https://openalex.org/W3124149531"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418"],"abstract_inverted_index":{"Current":[0],"approaches":[1],"to":[2,38,60,92,124,143,164,177,181],"statistical":[3],"parametric":[4],"speech":[5],"synthesis":[6],"using":[7,184],"Neural":[8],"Networks":[9],"generally":[10],"require":[11],"input":[12,71,163],"at":[13,30,47,74,166],"the":[14,19,48,53,62,70,80,117,149,161,167,185],"same":[15],"temporal":[16],"resolution":[17],"as":[18,103,105],"output,":[20],"typically":[21],"a":[22,56,66,156,175],"frame":[23,169],"every":[24],"5ms,":[25],"or":[26],"in":[27,65,128],"some":[28],"cases":[29],"waveform":[31],"sampling":[32],"rate.":[33,170],"It":[34],"is":[35,90,122],"therefore":[36],"necessary":[37],"fabricate":[39],"highly-redundant":[40],"frame-level":[41],"(or":[42],"sample":[43],"level)":[44],"linguistic":[45,72,162],"features":[46,73,99,121],"input.":[49],"This":[50],"paper":[51],"proposes":[52],"use":[54,96,118],"of":[55,97,119],"hierarchical":[57],"encoder-decoder":[58],"model":[59,89],"perform":[61],"sequence-to-sequence":[63],"regression":[64],"way":[67],"that":[68,148,159],"takes":[69],"their":[75],"original":[76],"timescales,":[77],"and":[78,85,134,174],"preserves":[79],"relationships":[81],"between":[82],"words,":[83],"syllables":[84],"phones.":[86],"The":[87],"proposed":[88,150],"designed":[91],"make":[93],"more":[94],"effective":[95],"suprasegmental":[98],"than":[100,155],"conventional":[101,157],"architectures,":[102],"well":[104],"being":[106],"computationally":[107],"efficient.":[108],"Experiments":[109],"were":[110],"conducted":[111],"on":[112,145],"prosodically-varied":[113],"audiobook":[114],"material":[115],"because":[116],"supra-segmental":[120],"thought":[123],"be":[125,165,182],"particularly":[126],"important":[127],"this":[129],"case.":[130],"Both":[131],"objective":[132],"measures":[133],"results":[135],"from":[136],"subjective":[137],"listening":[138],"tests,":[139],"which":[140],"asked":[141],"listeners":[142],"focus":[144],"prosody,":[146],"show":[147],"method":[151],"performs":[152],"significantly":[153],"better":[154],"architecture":[158],"requires":[160],"acoustic":[168],"<br/><br/>We":[171],"provide":[172],"code":[173],"recipe":[176],"enable":[178],"our":[179],"system":[180],"reproduced":[183],"Merlin":[186],"toolkit.":[187]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}