{"id":"https://openalex.org/W2964060510","doi":"https://doi.org/10.1109/icassp.2016.7472657","title":"Investigating gated recurrent networks for speech synthesis","display_name":"Investigating gated recurrent networks for speech synthesis","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2964060510","doi":"https://doi.org/10.1109/icassp.2016.7472657","mag":"2964060510"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/files/23749792/2016_Wu_King_Investigating_gates_recurrent_networks_for_speech_synthesis.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","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, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":129,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5140","last_page":"5144"},"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":0.9983999729156494,"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":0.9976000189781189,"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":0.8187633752822876},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7981008887290955},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6250895261764526},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5907174348831177},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5827029943466187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5777068734169006},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5389931797981262},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5233144760131836},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.5216313004493713},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.5191542506217957},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4699554443359375},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.467430055141449},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4315500259399414},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07943150401115417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187633752822876},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7981008887290955},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6250895261764526},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5907174348831177},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5827029943466187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5777068734169006},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5389931797981262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5233144760131836},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.5216313004493713},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.5191542506217957},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4699554443359375},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.467430055141449},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4315500259399414},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07943150401115417},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2016.7472657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/490b4b73-4be8-468c-8f75-f2e894b4197e","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/490b4b73-4be8-468c-8f75-f2e894b4197e","pdf_url":"https://www.research.ed.ac.uk/files/23749792/2016_Wu_King_Investigating_gates_recurrent_networks_for_speech_synthesis.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":"Wu, Z & King, S 2016, Investigating gated recurrent neural networks for speech synthesis. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 1-5, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 20/03/16. https://doi.org/10.1109/ICASSP.2016.7472657","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/490b4b73-4be8-468c-8f75-f2e894b4197e","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/490b4b73-4be8-468c-8f75-f2e894b4197e","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":"Wu, Z & King, S 2016, Investigating gated recurrent neural networks for speech synthesis. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 1-5, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 20/03/16. https://doi.org/10.1109/ICASSP.2016.7472657","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/490b4b73-4be8-468c-8f75-f2e894b4197e","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/490b4b73-4be8-468c-8f75-f2e894b4197e","pdf_url":"https://www.research.ed.ac.uk/files/23749792/2016_Wu_King_Investigating_gates_recurrent_networks_for_speech_synthesis.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":"Wu, Z & King, S 2016, Investigating gated recurrent neural networks for speech synthesis. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 1-5, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 20/03/16. https://doi.org/10.1109/ICASSP.2016.7472657","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/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"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964060510.pdf","grobid_xml":"https://content.openalex.org/works/W2964060510.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W581956982","https://openalex.org/W1499332833","https://openalex.org/W1543299179","https://openalex.org/W1571950845","https://openalex.org/W1576227399","https://openalex.org/W1613141907","https://openalex.org/W1689711448","https://openalex.org/W1815076433","https://openalex.org/W1924770834","https://openalex.org/W1990505856","https://openalex.org/W2045158511","https://openalex.org/W2049686551","https://openalex.org/W2064675550","https://openalex.org/W2078597717","https://openalex.org/W2079735306","https://openalex.org/W2102003408","https://openalex.org/W2106564373","https://openalex.org/W2107878631","https://openalex.org/W2129142580","https://openalex.org/W2134973740","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2157331557","https://openalex.org/W2294797155","https://openalex.org/W2394662942","https://openalex.org/W2395700867","https://openalex.org/W2397670047","https://openalex.org/W2399057275","https://openalex.org/W2404881427","https://openalex.org/W6616837769","https://openalex.org/W6634201745","https://openalex.org/W6637409405","https://openalex.org/W6638545294","https://openalex.org/W6640212811","https://openalex.org/W6675380101","https://openalex.org/W6696843773","https://openalex.org/W6711832335","https://openalex.org/W6712239235","https://openalex.org/W6712515775","https://openalex.org/W6713860685"],"related_works":["https://openalex.org/W3008584592","https://openalex.org/W4385280324","https://openalex.org/W2912153778","https://openalex.org/W4387163678","https://openalex.org/W4288108708","https://openalex.org/W2973430807","https://openalex.org/W2984436043","https://openalex.org/W4390245176","https://openalex.org/W2912831041","https://openalex.org/W2890685186"],"abstract_inverted_index":{"Recently,":[0],"recurrent":[1],"neural":[2,63],"networks":[3],"(RNNs)":[4],"as":[5,11,83],"powerful":[6],"sequence":[7,85],"models":[8],"have":[9,49],"re-emerged":[10],"a":[12,84,104,108,114,117],"potential":[13],"acoustic":[14],"model":[15,86],"for":[16,87,116],"statistical":[17],"parametric":[18],"speech":[19],"synthesis":[20],"(SPSS).":[21],"The":[22,120],"long":[23],"short-term":[24],"memory":[25],"(LSTM)":[26],"architecture":[27,122],"is":[28,66,99],"particularly":[29],"attractive":[30],"because":[31],"it":[32],"addresses":[33],"the":[34],"vanishing":[35],"gradient":[36],"problem":[37],"in":[38,113],"standard":[39],"RNNs,":[40],"making":[41],"them":[42],"easier":[43],"to":[44,73],"train.":[45],"Although":[46],"recent":[47],"studies":[48],"demonstrated":[50],"that":[51],"LSTMs":[52,80],"can":[53],"achieve":[54],"significantly":[55,124],"better":[56],"performance":[57],"on":[58],"SPSS":[59],"than":[60,127],"deep":[61],"feedforward":[62],"networks,":[64],"little":[65],"known":[67],"about":[68],"why.":[69],"Here":[70],"we":[71],"attempt":[72],"answer":[74],"two":[75],"questions:":[76],"a)":[77],"why":[78],"do":[79],"work":[81],"well":[82],"SPSS;":[88],"b)":[89],"which":[90],"component":[91],"(e.g.,":[92],"input":[93],"gate,":[94,96],"output":[95],"forget":[97],"gate)":[98],"most":[100],"important.":[101],"We":[102],"present":[103],"visual":[105],"analysis":[106],"alongside":[107],"series":[109],"of":[110],"experiments,":[111],"resulting":[112],"proposal":[115],"simplified":[118,121],"architecture.":[119],"has":[123],"fewer":[125],"parameters":[126],"an":[128],"LSTM,":[129],"thus":[130],"reducing":[131],"generation":[132],"complexity":[133],"considerably":[134],"without":[135],"degrading":[136],"quality.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":23},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}