{"id":"https://openalex.org/W2610284765","doi":"https://doi.org/10.21437/interspeech.2016-712","title":"Using Text and Acoustic Features in Predicting Glottal Excitation Waveforms for Parametric Speech Synthesis with Recurrent Neural Networks","display_name":"Using Text and Acoustic Features in Predicting Glottal Excitation Waveforms for Parametric Speech Synthesis with Recurrent Neural Networks","publication_year":2016,"publication_date":"2016-08-28","ids":{"openalex":"https://openalex.org/W2610284765","doi":"https://doi.org/10.21437/interspeech.2016-712","mag":"2610284765"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-712","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-712","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/a32f315b-f9fd-4926-814b-f87563b85047","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081575688","display_name":"Lauri Juvela","orcid":"https://orcid.org/0000-0002-2201-103X"},"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"]},{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI","JP"],"is_corresponding":false,"raw_author_name":"Lauri Juvela","raw_affiliation_strings":["Aalto University, Department of Signal Processing and Acoustics, Finland","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Department of Signal Processing and Acoustics, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[{"id":"https://openalex.org/I113766436","display_name":"Surugadai University","ror":"https://ror.org/00c4wmy51","country_code":"JP","type":"education","lineage":["https://openalex.org/I113766436"]},{"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":"Xin Wang","raw_affiliation_strings":["Sokendai University, Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sokendai University, Japan","institution_ids":["https://openalex.org/I113766436"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"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":"Shinji Takaki","raw_affiliation_strings":["National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013722514","display_name":"Manu Airaksinen","orcid":"https://orcid.org/0000-0002-8031-2260"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Manu Airaksinen","raw_affiliation_strings":["Aalto University, Department of Signal Processing and Acoustics, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Department of Signal Processing and Acoustics, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"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/I113766436","display_name":"Surugadai University","ror":"https://ror.org/00c4wmy51","country_code":"JP","type":"education","lineage":["https://openalex.org/I113766436"]},{"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"]},{"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","JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Japan","Sokendai University, Japan","University of Edinburgh, The Centre for Speech Technology Research, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"Sokendai University, Japan","institution_ids":["https://openalex.org/I113766436"]},{"raw_affiliation_string":"University of Edinburgh, The Centre for Speech Technology Research, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":["Aalto University, Department of Signal Processing and Acoustics, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Department of Signal Processing and Acoustics, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2283","last_page":"2287"},"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/T10863","display_name":"Voice and Speech Disorders","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.995199978351593,"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/speech-recognition","display_name":"Speech recognition","score":0.737307608127594},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.7309794425964355},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6990078687667847},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6751769185066223},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6193716526031494},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6189475655555725},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3835456967353821},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36025428771972656},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11297234892845154},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08647212386131287},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07082179188728333}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.737307608127594},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.7309794425964355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6990078687667847},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6751769185066223},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6193716526031494},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6189475655555725},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3835456967353821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36025428771972656},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11297234892845154},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08647212386131287},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07082179188728333},{"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.2016-712","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-712","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/a32f315b-f9fd-4926-814b-f87563b85047","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/a32f315b-f9fd-4926-814b-f87563b85047","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":"Juvela, L, Wang, X, Takaki, S, Airaksinen, M, Yamagishi, J & Alku, P 2016, Using Text and Acoustic Features in Predicting Glottal Excitation Waveforms for Parametric Speech Synthesis with Recurrent Neural Networks. in Interspeech 2016. International Speech Communication Association, International Speech Communication Association, pp. 2283-2287, Interspeech 2016, San Francisco, United States, 8/09/16. https://doi.org/10.21437/Interspeech.2016-712","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/a32f315b-f9fd-4926-814b-f87563b85047","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/using-text-and-acoustic-features-in-predicting-glottal-excitation-waveforms-for-parametric-speech-synthesis-with-recurrent-neural-networks(a32f315b-f9fd-4926-814b-f87563b85047).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/a32f315b-f9fd-4926-814b-f87563b85047","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/a32f315b-f9fd-4926-814b-f87563b85047","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":"Juvela, L, Wang, X, Takaki, S, Airaksinen, M, Yamagishi, J & Alku, P 2016, Using Text and Acoustic Features in Predicting Glottal Excitation Waveforms for Parametric Speech Synthesis with Recurrent Neural Networks. in Interspeech 2016. International Speech Communication Association, International Speech Communication Association, pp. 2283-2287, Interspeech 2016, San Francisco, United States, 8/09/16. https://doi.org/10.21437/Interspeech.2016-712","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3007105200","display_name":"Deep architectures for statistical speech synthesis","funder_award_id":"EP/J002526/1","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/G6082203376","display_name":null,"funder_award_id":"EP/J002526/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7878468599","display_name":null,"funder_award_id":"256961","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"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":26,"referenced_works":["https://openalex.org/W304834817","https://openalex.org/W1529628403","https://openalex.org/W1576227399","https://openalex.org/W1600722501","https://openalex.org/W1601809792","https://openalex.org/W1630569004","https://openalex.org/W1963637322","https://openalex.org/W1970278793","https://openalex.org/W2043003570","https://openalex.org/W2049686551","https://openalex.org/W2066999516","https://openalex.org/W2074854222","https://openalex.org/W2097634052","https://openalex.org/W2102003408","https://openalex.org/W2107449214","https://openalex.org/W2111284386","https://openalex.org/W2125118056","https://openalex.org/W2129082420","https://openalex.org/W2129142580","https://openalex.org/W2149572519","https://openalex.org/W2294797155","https://openalex.org/W2395578248","https://openalex.org/W2398742733","https://openalex.org/W2405614646","https://openalex.org/W2406009315","https://openalex.org/W4301202368"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W2176409448","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672","https://openalex.org/W4367555392","https://openalex.org/W2883092465","https://openalex.org/W2039489009"],"abstract_inverted_index":{"This":[0],"work":[1],"studies":[2],"the":[3,77,86,94,97],"use":[4],"of":[5,96],"deep":[6,31],"learning":[7],"methods":[8],"to":[9,67,93],"directly":[10,89],"model":[11],"glottal":[12,74,112],"excitation":[13,98,115],"waveforms":[14,75],"from":[15,76,99],"context":[16],"dependent":[17],"text":[18,37,65,78,87],"features":[19,40,66,69,88],"in":[20,59,63,72],"a":[21,30,104,110],"text-to-speech":[22,34],"synthesis":[23],"system.":[24],"Glottal":[25],"vocoding":[26],"is":[27],"integrated":[28],"into":[29],"neural":[32,55],"network-based":[33],"framework":[35],"where":[36],"and":[38,70],"acoustic":[39,68,80,100],"can":[41],"be":[42],"flexibly":[43],"used":[44],"as":[45],"both":[46,102],"network":[47],"inputs":[48],"or":[49],"outputs.":[50],"Long":[51],"short-term":[52],"memory":[53],"recurrent":[54],"networks":[56],"are":[57],"utilised":[58],"two":[60],"stages:":[61],"first,":[62],"mapping":[64],"second,":[71],"predicting":[73],"and/or":[79],"features.":[81],"Results":[82],"show":[83],"that":[84],"using":[85,109],"yields":[90],"similar":[91],"quality":[92],"prediction":[95],"features,":[101],"outperforming":[103],"baseline":[105],"system":[106],"based":[107],"on":[108],"fixed":[111],"pulse":[113],"for":[114],"generation.":[116]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}