{"id":"https://openalex.org/W2801554275","doi":"https://doi.org/10.1109/taslp.2018.2828980","title":"Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech","display_name":"Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech","publication_year":2018,"publication_date":"2018-04-20","ids":{"openalex":"https://openalex.org/W2801554275","doi":"https://doi.org/10.1109/taslp.2018.2828980","mag":"2801554275"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2828980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2828980","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/58246045/Cassia_SpeechEnhancement_Journal.pdf","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":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K"],"raw_orcid":"https://orcid.org/0000-0002-3486-8620","affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"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/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":["Centre for Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, U.K","National Institute of Informatics, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2752-3955","affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":3.1954,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":{"value":0.92915999,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"26","issue":"8","first_page":"1420","last_page":"1433"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9898999929428101,"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-recognition","display_name":"Speech recognition","score":0.6642928123474121},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49908018112182617},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4824593663215637},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.4558521509170532},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.45472943782806396},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4519311487674713},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4350307881832123},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2837558388710022},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.20843827724456787},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06039929389953613}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6642928123474121},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49908018112182617},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4824593663215637},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.4558521509170532},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.45472943782806396},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4519311487674713},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4350307881832123},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2837558388710022},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.20843827724456787},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06039929389953613}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2018.2828980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2828980","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/1b323f2a-b827-419a-8d2e-6b7bfe083e92","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/1b323f2a-b827-419a-8d2e-6b7bfe083e92","pdf_url":"https://www.research.ed.ac.uk/files/58246045/Cassia_SpeechEnhancement_Journal.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":"Valentini Botinhao, C & Yamagishi, J 2018, 'Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 26, no. 8, pp. 1420-1433. https://doi.org/10.1109/TASLP.2018.2828980","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.ed.ac.uk:publications/1b323f2a-b827-419a-8d2e-6b7bfe083e92","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/1b323f2a-b827-419a-8d2e-6b7bfe083e92","pdf_url":"https://www.research.ed.ac.uk/files/58246045/Cassia_SpeechEnhancement_Journal.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":"Valentini Botinhao, C & Yamagishi, J 2018, 'Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 26, no. 8, pp. 1420-1433. https://doi.org/10.1109/TASLP.2018.2828980","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/1b323f2a-b827-419a-8d2e-6b7bfe083e92","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/1b323f2a-b827-419a-8d2e-6b7bfe083e92","pdf_url":"https://www.research.ed.ac.uk/files/58246045/Cassia_SpeechEnhancement_Journal.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":"Valentini Botinhao, C & Yamagishi, J 2018, 'Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 26, no. 8, pp. 1420-1433. https://doi.org/10.1109/TASLP.2018.2828980","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G2153275282","display_name":null,"funder_award_id":"EP/I031022/1 (NST)","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"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/G7431146739","display_name":null,"funder_award_id":"EP/J002526/1 (CAF)","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7623259429","display_name":"Robust voice cloning technologies in noisy environments and its applications","funder_award_id":"17H04687","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2801554275.pdf","grobid_xml":"https://content.openalex.org/works/W2801554275.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W190060899","https://openalex.org/W304834817","https://openalex.org/W333180468","https://openalex.org/W1516533146","https://openalex.org/W1516630152","https://openalex.org/W1547848553","https://openalex.org/W1552314771","https://openalex.org/W1897240248","https://openalex.org/W1983108229","https://openalex.org/W1996304098","https://openalex.org/W2000513720","https://openalex.org/W2005768155","https://openalex.org/W2006129368","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2049686551","https://openalex.org/W2067295501","https://openalex.org/W2070126272","https://openalex.org/W2109754985","https://openalex.org/W2111867421","https://openalex.org/W2117418893","https://openalex.org/W2120847449","https://openalex.org/W2126942983","https://openalex.org/W2127327781","https://openalex.org/W2133908567","https://openalex.org/W2140828385","https://openalex.org/W2146324387","https://openalex.org/W2153914468","https://openalex.org/W2154920538","https://openalex.org/W2165534711","https://openalex.org/W2172491908","https://openalex.org/W2188162373","https://openalex.org/W2242685705","https://openalex.org/W2395578248","https://openalex.org/W2408688265","https://openalex.org/W2514828952","https://openalex.org/W2557915412","https://openalex.org/W2603567530","https://openalex.org/W2741913599","https://openalex.org/W2747161606","https://openalex.org/W2747732471","https://openalex.org/W2749609415","https://openalex.org/W2762693443","https://openalex.org/W2774389566","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963453742","https://openalex.org/W4245919820","https://openalex.org/W6610843619","https://openalex.org/W6611394673","https://openalex.org/W6630961876","https://openalex.org/W6680017764","https://openalex.org/W6686978693","https://openalex.org/W6711777497","https://openalex.org/W6714016741","https://openalex.org/W6729924827","https://openalex.org/W6740049204","https://openalex.org/W6745258804","https://openalex.org/W6941384618","https://openalex.org/W6982686887"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W3110551121","https://openalex.org/W4388404911","https://openalex.org/W2105439218","https://openalex.org/W2066051122","https://openalex.org/W2147998355"],"abstract_inverted_index":{"Text-to-speech":[0],"voices":[1,119],"created":[2,80],"from":[3],"noisy":[4],"and":[5,38,48,68,92,109,112,160,166],"reverberant":[6],"recordings":[7,25,71,83,89],"are":[8],"of":[9,23,66,72,84,90,118],"lower":[10,69,75,122],"quality.":[11],"A":[12],"simple":[13],"way":[14],"to":[15,19,27,49,87],"improve":[16],"this":[17,41,46],"is":[18,61],"increase":[20],"the":[21,24,51,139,142,150,157,170],"quality":[22,70,76,117,123],"prior":[26],"text-to-speech":[28],"training":[29],"with":[30,63,98,106,121,153],"speech":[31,91],"enhancement":[32],"methods":[33],"such":[34],"as":[35,147,149],"noise":[36,86,114,165],"suppression":[37],"dereverberation.":[39],"In":[40],"paper,":[42],"we":[43,53],"opted":[44],"for":[45],"approach":[47],"perform":[50],"enhancement,":[52],"used":[54],"a":[55],"recurrent":[56],"neural":[57],"network.":[58],"The":[59,74,116],"network":[60],"trained":[62,103,120,152],"parallel":[64],"data":[65,77,124],"clean":[67,100,154],"speech.":[73],"was":[78,132],"artificially":[79],"by":[81,93],"adding":[82],"environmental":[85],"studio-quality":[88],"convolving":[94],"room":[95],"impulse":[96],"responses":[97],"these":[99,130],"recordings.":[101],"We":[102],"separate":[104],"networks":[105,131],"noise-only,":[107],"reverberation-only,":[108],"both":[110,164],"reverberation":[111,167],"additive":[113],"data.":[115,155],"that":[125],"has":[126],"been":[127],"enhanced":[128,143],"using":[129],"significantly":[133],"higher":[134],"in":[135],"all":[136],"cases.":[137],"For":[138,156],"noise-only":[140],"case,":[141],"synthetic":[144],"voice":[145,151],"ranked":[146],"high":[148],"most":[158],"realistic":[159],"challenging":[161],"scenario,":[162],"when":[163],"were":[168,172],"present,":[169],"improvements":[171],"more":[173],"modest,":[174],"but":[175],"still":[176],"significant.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":3}],"updated_date":"2026-08-31T07:19:18.363097","created_date":"2025-10-10T00:00:00"}