{"id":"https://openalex.org/W2404881427","doi":"https://doi.org/10.21437/interspeech.2015-265","title":"Fusion of multiple parameterisations for DNN-based sinusoidal speech synthesis with multi-task learning","display_name":"Fusion of multiple parameterisations for DNN-based sinusoidal speech synthesis with multi-task learning","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2404881427","doi":"https://doi.org/10.21437/interspeech.2015-265","mag":"2404881427"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-265","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/20169196/Qiong_DNN_Synthesis_Sinusoidal.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032437290","display_name":"Qiong Hu","orcid":"https://orcid.org/0000-0002-7525-1387"},"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":"Qiong Hu","raw_affiliation_strings":["The Centre for Speech Technology Research,University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research,University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"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":"Zhizheng Wu","raw_affiliation_strings":["The Centre for Speech Technology Research,University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research,University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"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":"Korin Richmond","raw_affiliation_strings":["The Centre for Speech Technology Research,University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research,University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"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":"Junichi Yamagishi","raw_affiliation_strings":["The Centre for Speech Technology Research,University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research,University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":["Toshiba Research Europe Ltd, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110289715","display_name":"Ranniery Maia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ranniery Maia","raw_affiliation_strings":["Toshiba Research Europe Ltd, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.0131,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.97442653,"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":"854","last_page":"858"},"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":0.9966999888420105,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7596831321716309},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5892466902732849},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5682981014251709},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5445747971534729},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5421553254127502},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5264514088630676},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5006873607635498},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4653492867946625},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4377838373184204},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36725014448165894},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3216041624546051},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12175077199935913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596831321716309},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5892466902732849},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5682981014251709},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5445747971534729},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5421553254127502},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5264514088630676},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5006873607635498},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4653492867946625},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4377838373184204},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36725014448165894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3216041624546051},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12175077199935913},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2015-265","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/7d331880-cf4d-4188-b127-47b6887fba2a","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/7d331880-cf4d-4188-b127-47b6887fba2a","pdf_url":"https://www.pure.ed.ac.uk/ws/files/20169196/Qiong_DNN_Synthesis_Sinusoidal.pdf","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":"Hu, Q, Wu, Z, Richmond, K, Yamagishi, J, Stylianou, Y & Maia, R 2015, Fusion of multiple parameterisations for DNN-based sinusoidal speech synthesis with multi-task learning. in INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association. International Speech Communication Association, pp. 854-858. < http://www.isca-speech.org/archive/interspeech_2015/i15_0854.html >","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/7d331880-cf4d-4188-b127-47b6887fba2a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/7d331880-cf4d-4188-b127-47b6887fba2a","pdf_url":"https://www.pure.ed.ac.uk/ws/files/20169196/Qiong_DNN_Synthesis_Sinusoidal.pdf","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:publications/7d331880-cf4d-4188-b127-47b6887fba2a","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/7d331880-cf4d-4188-b127-47b6887fba2a","pdf_url":"https://www.pure.ed.ac.uk/ws/files/20169196/Qiong_DNN_Synthesis_Sinusoidal.pdf","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":"Hu, Q, Wu, Z, Richmond, K, Yamagishi, J, Stylianou, Y & Maia, R 2015, Fusion of multiple parameterisations for DNN-based sinusoidal speech synthesis with multi-task learning. in INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association. International Speech Communication Association, pp. 854-858. < http://www.isca-speech.org/archive/interspeech_2015/i15_0854.html >","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2404881427.pdf","grobid_xml":"https://content.openalex.org/works/W2404881427.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W95551363","https://openalex.org/W111544860","https://openalex.org/W173856587","https://openalex.org/W1494715773","https://openalex.org/W1499332833","https://openalex.org/W1563460361","https://openalex.org/W1600722501","https://openalex.org/W1601809792","https://openalex.org/W1963637322","https://openalex.org/W1968944773","https://openalex.org/W1990505856","https://openalex.org/W1998915416","https://openalex.org/W2000513720","https://openalex.org/W2049686551","https://openalex.org/W2066999516","https://openalex.org/W2074854222","https://openalex.org/W2102003408","https://openalex.org/W2115856579","https://openalex.org/W2117130368","https://openalex.org/W2129142580","https://openalex.org/W2134973740","https://openalex.org/W2154920538","https://openalex.org/W2160815625","https://openalex.org/W2231075402","https://openalex.org/W2276892362","https://openalex.org/W2396366106","https://openalex.org/W3209042722"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2176409448","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672","https://openalex.org/W4367555392","https://openalex.org/W2039489009","https://openalex.org/W127416991"],"abstract_inverted_index":{"It":[0],"has":[1,29],"recently":[2],"been":[3,93],"shown":[4,31],"that":[5,32,71,91,192],"deep":[6],"neural":[7],"networks":[8],"(DNN)":[9],"can":[10],"improve":[11],"the":[12,116,167,185],"quality":[13],"of":[14,118,163],"statistical":[15],"parametric":[16],"speech":[17],"synthesis":[18,89],"(SPSS)":[19],"when":[20],"using":[21,62,173],"a":[22,33,53,77,81,170],"source-filter":[23],"vocoder.":[24],"Our":[25,148],"own":[26],"previous":[27],"work":[28,72],"furthermore":[30],"dynamic":[34],"sinusoidal":[35],"model":[36,135],"(DSM)":[37],"is":[38,180],"also":[39],"highly":[40],"suited":[41],"to":[42,75,95,110,130,134,195],"DNN-based":[43],"SPSS,":[44],"whereby":[45],"sinusoids":[46],"may":[47,59,98],"either":[48],"be":[49,60],"used":[50],"themselves":[51],"as":[52,143],"\"direct":[54],"parameterisation\"":[55,66],"(DIR),":[56],"or":[57],"they":[58],"encoded":[61],"an":[63],"\"intermediate":[64],"spectral":[65],"(INT).":[67],"The":[68],"approach":[69],"in":[70,105],"was":[73],"effectively":[74],"replace":[76],"decision":[78],"tree":[79],"with":[80,198],"neura":[82],"l":[83],"network.":[84],"However,":[85],"waveform":[86,123],"parameterisation":[87],"and":[88,113,122,139,145,191,199],"steps":[90],"have":[92],"developed":[94],"suit":[96],"HMMs":[97],"not":[99],"fully":[100],"exploit":[101],"DNN":[102,120,126],"capabilities.":[103],"Here,":[104],"contrast,":[106],"we":[107,128],"investigate":[108],"ways":[109],"combine":[111],"INT":[112],"DIR":[114],"at":[115],"levels":[117],"both":[119,157,178,197],"modelling":[121,154],"generation.":[124],"For":[125],"training,":[127],"propose":[129],"use":[131],"multi-task":[132],"learning":[133],"cepstra":[136],"(from":[137],"INT)":[138],"log":[140],"amplitudes(from":[141],"DIR)":[142],"primary":[144],"secondary":[146],"tasks.":[147,158],"results":[149],"show":[150,184],"combining":[151],"these":[152],"improves":[153],"accuracy":[155],"for":[156],"Next,":[159],"during":[160],"synthesis,":[161],"instead":[162],"discarding":[164],"parameters":[165],"from":[166,177],"second":[168],"task,":[169],"fusion":[171],"method":[172,187],"harmonic":[174],"amplitudes":[175],"derived":[176],"tasks":[179],"applied.":[181],"Preference":[182],"tests":[183],"proposed":[186],"gives":[188],"improved":[189],"performance,":[190],"this":[193],"applies":[194],"synthesising":[196],"without":[200],"global":[201],"variance":[202],"parameters.":[203]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":11}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}