{"id":"https://openalex.org/W2514828952","doi":"https://doi.org/10.21437/interspeech.2016-159","title":"Speech Enhancement for a Noise-Robust Text-to-Speech Synthesis System Using Deep Recurrent Neural Networks","display_name":"Speech Enhancement for a Noise-Robust Text-to-Speech Synthesis System Using Deep Recurrent Neural Networks","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2514828952","doi":"https://doi.org/10.21437/interspeech.2016-159","mag":"2514828952"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-159","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-159","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://hdl.handle.net/20.500.11820/08deb6fd-79c0-490f-ae46-f37034b6bfb4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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 (CSTR), University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"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"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["National Institute of Informatics, Japan","SOKENDAI University, Japan"],"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","https://openalex.org/I200475212"]}]},{"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":"last","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/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]},{"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","The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"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","https://openalex.org/I200475212"]},{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":121,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"352","last_page":"356"},"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":0.9998999834060669,"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":0.9986000061035156,"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/speech-enhancement","display_name":"Speech enhancement","score":0.7503907680511475},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6924604177474976},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6852424740791321},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5565276145935059},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5528801679611206},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.518351674079895},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4933256208896637},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4572531580924988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3991241753101349},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1631479561328888}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7503907680511475},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6924604177474976},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6852424740791321},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5565276145935059},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5528801679611206},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.518351674079895},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4933256208896637},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4572531580924988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3991241753101349},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1631479561328888},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2016-159","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-159","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:publications/08deb6fd-79c0-490f-ae46-f37034b6bfb4","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/08deb6fd-79c0-490f-ae46-f37034b6bfb4","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":"Valentini Botinhao, C, Wang, X, Takaki, S & Yamagishi, J 2016, Speech Enhancement for a Noise-Robust Text-to-Speech Synthesis System using Deep Recurrent Neural Networks. in Proceedings of Interspeech 2016. Interspeech, San Francisco, United States, pp. 352-356, Interspeech 2016, San Francisco, United States, 8/09/16. https://doi.org/10.21437/Interspeech.2016-159","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.ed.ac.uk:publications/08deb6fd-79c0-490f-ae46-f37034b6bfb4","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/08deb6fd-79c0-490f-ae46-f37034b6bfb4","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:pure.ed.ac.uk:publications/08deb6fd-79c0-490f-ae46-f37034b6bfb4","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/08deb6fd-79c0-490f-ae46-f37034b6bfb4","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":"Valentini Botinhao, C, Wang, X, Takaki, S & Yamagishi, J 2016, Speech Enhancement for a Noise-Robust Text-to-Speech Synthesis System using Deep Recurrent Neural Networks. in Proceedings of Interspeech 2016. Interspeech, San Francisco, United States, pp. 352-356, Interspeech 2016, San Francisco, United States, 8/09/16. https://doi.org/10.21437/Interspeech.2016-159","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"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"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W5151113","https://openalex.org/W304834817","https://openalex.org/W1495679096","https://openalex.org/W1499864241","https://openalex.org/W1516630152","https://openalex.org/W1576227399","https://openalex.org/W1592103878","https://openalex.org/W1897240248","https://openalex.org/W1983108229","https://openalex.org/W2000513720","https://openalex.org/W2005768155","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2049036695","https://openalex.org/W2049686551","https://openalex.org/W2064675550","https://openalex.org/W2094721231","https://openalex.org/W2106564373","https://openalex.org/W2107878631","https://openalex.org/W2111867421","https://openalex.org/W2116261113","https://openalex.org/W2129142580","https://openalex.org/W2136848157","https://openalex.org/W2143612262","https://openalex.org/W2146324387","https://openalex.org/W2153914468","https://openalex.org/W2154920538","https://openalex.org/W2294797155","https://openalex.org/W2394662942","https://openalex.org/W2399057275","https://openalex.org/W2408688265","https://openalex.org/W2804690068"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W2578422401","https://openalex.org/W2770665941","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W197907117"],"abstract_inverted_index":{"Quality":[0],"of":[1,19,42,52,58,74,82],"text-to-speech":[2],"voices":[3],"built":[4,110],"from":[5],"noisy":[6,43,80,123],"recordings":[7],"is":[8],"diminished.":[9],"In":[10],"order":[11],"to":[12,24,29,93],"improve":[13],"it":[14,147],"we":[15],"propose":[16],"the":[17,53,75,108,119,143],"use":[18],"a":[20,33,39,79,132,153],"recurrent":[21,35],"neural":[22,36],"network":[23,37,88],"enhance":[25],"acoustic":[26,97],"parameters":[27,47,113],"prior":[28],"training.":[30],"We":[31,65,77],"trained":[32,121,155],"deep":[34],"using":[38,67,86,131],"parallel":[40],"database":[41,56,81],"and":[44,50,61,89,125],"clean":[45,157],"acoustics":[46],"as":[48,70,150,152],"input":[49,73],"output":[51,92],"network.":[54,76],"The":[55,136],"consisted":[57],"multiple":[59],"speakers":[60,85],"diverse":[62],"noise":[63],"conditions.":[64],"investigated":[66],"text-derived":[68,137],"features":[69,138],"an":[71,95],"additional":[72],"processed":[78],"two":[83],"other":[84],"this":[87],"used":[90],"its":[91],"train":[94],"HMM":[96],"text-to-synthesis":[98],"model":[99],"for":[100,142],"each":[101],"voice.":[102],"Listening":[103],"experiment":[104],"results":[105,140],"showed":[106],"that":[107,127],"voice":[109,154],"with":[111,122,156],"enhanced":[112,130],"was":[114,148],"ranked":[115,149],"significantly":[116],"higher":[117],"than":[118],"ones":[120],"speech":[124,126],"has":[128],"been":[129],"conventional":[133],"enhancement":[134],"system.":[135],"improved":[139],"only":[141],"female":[144],"voice,":[145],"where":[146],"highly":[151],"speech.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}