{"id":"https://openalex.org/W2517736208","doi":"https://doi.org/10.21437/interspeech.2016-1034","title":"Syllable-Level Representations of Suprasegmental Features for DNN-Based Text-to-Speech Synthesis","display_name":"Syllable-Level Representations of Suprasegmental Features for DNN-Based Text-to-Speech Synthesis","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2517736208","doi":"https://doi.org/10.21437/interspeech.2016-1034","mag":"2517736208"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-1034","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-1034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/d6a2da8f-a858-4be8-b278-7534e627080d","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109494794","display_name":"Manuel Sam Ribeiro","orcid":"https://orcid.org/0000-0001-8096-2231"},"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":"Manuel Sam Ribeiro","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, 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":["Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3186","last_page":"3190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9973999857902527,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9958999752998352,"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/syllable","display_name":"Syllable","score":0.7508436441421509},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7175838947296143},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6798679828643799},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6445541977882385},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4825422167778015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43255582451820374}],"concepts":[{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.7508436441421509},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7175838947296143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6798679828643799},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6445541977882385},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4825422167778015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43255582451820374}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2016-1034","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-1034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/d6a2da8f-a858-4be8-b278-7534e627080d","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/d6a2da8f-a858-4be8-b278-7534e627080d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Ribeiro, M S, Watts, O & Yamagishi, J 2016, Syllable-Level Representations of Suprasegmental Features for DNN-Based Text-to-Speech Synthesis. in Interspeech 2016. International Speech Communication Association, pp. 3186-3190, Interspeech 2016, San Francisco, United States, 8/09/16. https://doi.org/10.21437/Interspeech.2016-1034","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/d6a2da8f-a858-4be8-b278-7534e627080d","is_oa":false,"landing_page_url":"http://www.isca-speech.org/archive/Interspeech_2016/abstracts/1034.html","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/d6a2da8f-a858-4be8-b278-7534e627080d","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/d6a2da8f-a858-4be8-b278-7534e627080d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Ribeiro, M S, Watts, O & Yamagishi, J 2016, Syllable-Level Representations of Suprasegmental Features for DNN-Based Text-to-Speech Synthesis. in Interspeech 2016. International Speech Communication Association, pp. 3186-3190, Interspeech 2016, San Francisco, United States, 8/09/16. https://doi.org/10.21437/Interspeech.2016-1034","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2265749999","display_name":"DTA - University of Edinburgh","funder_award_id":"EP/K503034/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"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/G5810626578","display_name":null,"funder_award_id":"CRSII2 141903","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"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":24,"referenced_works":["https://openalex.org/W251642908","https://openalex.org/W397522103","https://openalex.org/W1499332833","https://openalex.org/W1517939602","https://openalex.org/W1540083112","https://openalex.org/W1571950845","https://openalex.org/W1578102511","https://openalex.org/W1614298861","https://openalex.org/W1977362129","https://openalex.org/W2029190953","https://openalex.org/W2029434926","https://openalex.org/W2078597717","https://openalex.org/W2102003408","https://openalex.org/W2106564373","https://openalex.org/W2109938215","https://openalex.org/W2111284386","https://openalex.org/W2139525902","https://openalex.org/W2184310502","https://openalex.org/W2187089797","https://openalex.org/W2296111744","https://openalex.org/W2394662942","https://openalex.org/W2395380967","https://openalex.org/W2950577311","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2891881129","https://openalex.org/W2514064218","https://openalex.org/W2094188777","https://openalex.org/W2112609279","https://openalex.org/W2132658536","https://openalex.org/W1581825163","https://openalex.org/W2399404538","https://openalex.org/W3204019825","https://openalex.org/W2366310385","https://openalex.org/W2061937230"],"abstract_inverted_index":{"A":[0,121],"top-down":[1],"hierarchical":[2,70,99],"system":[3,71,100,113],"based":[4],"on":[5],"deep":[6],"neural":[7],"networks":[8],"is":[9,35,42,81,95,101,128],"investigated":[10],"for":[11,61],"the":[12,62,69,76,85,98,119,125,136],"modeling":[13],"of":[14,32,124,135],"prosody":[15],"in":[16],"speech":[17],"synthesis.":[18],"Suprasegmental":[19],"features":[20,26,57,66,106],"are":[21,72,92],"processed":[22],"separately":[23],"from":[24,89],"segmental":[25,54],"and":[27,55,130],"a":[28,46,78,112,133],"compact":[29],"distributed":[30],"representation":[31,41,80],"high-level":[33],"units":[34],"learned":[36,88],"at":[37,84,107,118],"syllable-level.":[38],"The":[39],"suprasegmental":[40,56],"then":[43,73],"integrated":[44],"into":[45,68],"frame-level":[47,63],"network.":[48,64],"Objective":[49],"measures":[50],"show":[51],"that":[52,97],"balancing":[53],"can":[58],"be":[59],"useful":[60],"Additional":[65],"incorporated":[67],"tested.":[74],"At":[75],"syllable-level,":[77],"bag-of-phones":[79],"proposed":[82,126],"and,":[83],"word-level,":[86],"embeddings":[87],"text":[90],"sources":[91],"used.":[93],"It":[94],"shown":[96],"able":[102],"to":[103],"leverage":[104],"new":[105],"higher-levels":[108],"more":[109],"efficiently":[110],"than":[111],"which":[114],"exploits":[115],"them":[116],"directly":[117],"frame-level.":[120],"perceptual":[122],"evaluation":[123],"systems":[127],"conducted":[129],"followed":[131],"by":[132],"discussion":[134],"results.":[137]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}