{"id":"https://openalex.org/W2972569067","doi":"https://doi.org/10.21437/ssw.2019-39","title":"Where do the improvements come from in sequence-to-sequence neural TTS?","display_name":"Where do the improvements come from in sequence-to-sequence neural TTS?","publication_year":2019,"publication_date":"2019-09-14","ids":{"openalex":"https://openalex.org/W2972569067","doi":"https://doi.org/10.21437/ssw.2019-39","mag":"2972569067"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2019-39","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-39","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-268195","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Oliver Watts","raw_affiliation_strings":["The Centre for Speech Technology Research, The University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Gustav Eje Henter","raw_affiliation_strings":["Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043162691","display_name":"Jason Fong","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":"Jason Fong","raw_affiliation_strings":["The Centre for Speech Technology Research, The University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"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":"Cassia Valentini-Botinhao","raw_affiliation_strings":["The Centre for Speech Technology Research, The University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110238677"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":3.1791,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.93678685,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"217","last_page":"222"},"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":0.9994000196456909,"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/T10320","display_name":"Neural Networks and Applications","score":0.9959999918937683,"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/sequence","display_name":"Sequence (biology)","score":0.7834679484367371},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6182457804679871},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46337026357650757},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4601624011993408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3775697946548462},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08290252089500427},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.06580942869186401}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7834679484367371},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6182457804679871},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46337026357650757},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4601624011993408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3775697946548462},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08290252089500427},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.06580942869186401}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/ssw.2019-39","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-39","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:kth-268195","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-268195","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":null,"raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/659cc525-129f-40ed-84f5-15f1cc1c24af","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/659cc525-129f-40ed-84f5-15f1cc1c24af","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":"Watts, O, Henter, G, Fong, J & Valentini-Botinhao, C 2019, Where do the improvements come from in sequence-to-sequence neural TTS? in 10th ISCA Speech Synthesis Workshop. International Speech Communication Association, pp. 217-222, The 10th ISCA Speech Synthesis Workshop, Vienna, Austria, 20/09/19. https://doi.org/10.21437/SSW.2019-39","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/659cc525-129f-40ed-84f5-15f1cc1c24af","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/659cc525-129f-40ed-84f5-15f1cc1c24af","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-268195","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-268195","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2876024447","display_name":null,"funder_award_id":"RIT15-0107","funder_id":"https://openalex.org/F4320320940","funder_display_name":"Stiftelsen f\u00f6r\u00a0Strategisk Forskning"},{"id":"https://openalex.org/G5316222358","display_name":"SCRIPT: Speech Synthesis for Spoken Content Production","funder_award_id":"EP/P011586/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8719353587","display_name":null,"funder_award_id":"EP/P0","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320940","display_name":"Stiftelsen f\u00f6r\u00a0Strategisk Forskning","ror":"https://ror.org/044wr7g58"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1496801689","https://openalex.org/W1576227399","https://openalex.org/W1902237438","https://openalex.org/W2120847449","https://openalex.org/W2154920538","https://openalex.org/W2400063444","https://openalex.org/W2402539796","https://openalex.org/W2471520273","https://openalex.org/W2515943672","https://openalex.org/W2598638573","https://openalex.org/W2767052532","https://openalex.org/W2794490148","https://openalex.org/W2964243274","https://openalex.org/W4231807801"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Sequence-to-sequence":[0],"neural":[1,125],"networks":[2],"with":[3,14,41,119],"attention":[4],"mechanisms":[5],"have":[6,70],"recently":[7],"been":[8,71],"widely":[9],"adopted":[10],"for":[11],"text-to-speech.":[12],"Compared":[13],"older,":[15],"more":[16],"modular":[17,115],"statistical":[18],"parametric":[19],"synthesis":[20],"systems,":[21],"sequence-to-sequence":[22,126],"systems":[23,76,148,159],"feature":[24],"three":[25],"prominent":[26],"innovations:":[27],"1)":[28],"They":[29,46,62],"replace":[30],"substantial":[31],"parts":[32],"of":[33,92,106,111,157,168,180],"traditional":[34],"fixed":[35],"front-end":[36],"processing":[37],"pipelines":[38],"(like":[39],"Festival's)":[40],"learned":[42],"text":[43,51],"analysis;":[44],"2)":[45],"jointly":[47],"learn":[48],"to":[49,55,74,87,97,136,145,163],"align":[50],"and":[52,54,131,139,143,178],"speech":[53,57],"synthesise":[56],"audio":[58],"from":[59],"text;":[60],"3)":[61],"operate":[63],"autoregressively":[64],"on":[65,174],"previously-generated":[66],"acoustics.":[67],"Naturalness":[68],"improvements":[69],"reported":[72],"relative":[73],"earlier":[75],"which":[77],"do":[78],"not":[79],"contain":[80],"these":[81,158],"innovations.":[82,171],"It":[83],"would":[84],"be":[85],"useful":[86],"know":[88],"how":[89],"much":[90],"each":[91],"the":[93,98,108,120,152,165,169,175],"various":[94,141,170],"innovations":[95],"contribute":[96],"improved":[99],"performance.":[100],"We":[101,172],"here":[102],"propose":[103],"one":[104],"way":[105],"associating":[107],"separately-learned":[109],"components":[110,142],"a":[112],"representative":[113],"older":[114],"system,":[116],"specifically":[117,128],"Merlin,":[118],"different":[121],"sub-networks":[122],"within":[123],"recent":[124],"architectures,":[127],"Tacotron":[129],"2":[130],"DCTTS.":[132],"This":[133],"allows":[134,161],"us":[135,162],"swap":[137],"in":[138],"out":[140],"subnets":[144],"produce":[146],"intermediate":[147],"that":[149],"step":[150],"between":[151],"two":[153],"paradigms;":[154],"subjective":[155],"evaluation":[156],"then":[160],"isolate":[164],"perceptual":[166],"effects":[167],"report":[173],"design,":[176],"evaluation,":[177],"findings":[179],"such":[181],"an":[182],"experiment.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}