{"id":"https://openalex.org/W2603567530","doi":"https://doi.org/10.21437/ssw.2016-24","title":"Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech","display_name":"Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech","publication_year":2016,"publication_date":"2016-09-13","ids":{"openalex":"https://openalex.org/W2603567530","doi":"https://doi.org/10.21437/ssw.2016-24","mag":"2603567530"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2016-24","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2016-24","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cassia Valentini-Botinhao","raw_affiliation_strings":["School of Informatics"],"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Takaki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Informatics"],"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019012876"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.1617,"has_fulltext":false,"cited_by_count":463,"citation_normalized_percentile":{"value":0.98413906,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"152"},"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":0.9997000098228455,"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":0.9968000054359436,"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":0.739267110824585},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7095099687576294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7054861187934875},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4646090567111969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3201040029525757},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21660274267196655}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.739267110824585},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7095099687576294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7054861187934875},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4646090567111969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3201040029525757},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21660274267196655},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/ssw.2016-24","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2016-24","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/bc55fa58-067a-40bb-80c8-c76c98bae50f","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/bc55fa58-067a-40bb-80c8-c76c98bae50f","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":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W304834817","https://openalex.org/W1499864241","https://openalex.org/W1516630152","https://openalex.org/W1547848553","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/W2049686551","https://openalex.org/W2064675550","https://openalex.org/W2094721231","https://openalex.org/W2106564373","https://openalex.org/W2107878631","https://openalex.org/W2111867421","https://openalex.org/W2129142580","https://openalex.org/W2130813098","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/W2514828952","https://openalex.org/W2804690068"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W3096184950","https://openalex.org/W2770665941","https://openalex.org/W2782782444"],"abstract_inverted_index":{"The":[0,71,131],"quality":[1,23],"of":[2],"text-to-speech":[3],"(TTS)":[4],"voices":[5,25,181,198],"built":[6,26],"from":[7,63,127,139],"noisy":[8,64,140],"speech":[9,14,29,42,65,114,141],"is":[10,74,149],"compromised.":[11],"Enhancing":[12],"the":[13,79,88,109,123,128,136,146,158,164],"data":[15,73,184],"before":[16],"training":[17],"has":[18],"been":[19],"shown":[20],"to":[21,44,58,66,77,92,144,152,156,195,197],"improve":[22],"but":[24,172],"with":[27,183,186,193,200],"clean":[28,69,201],"are":[30,142],"still":[31],"preferred.":[32],"In":[33,48,83,108],"this":[34,187],"paper":[35],"we":[36,51,86,117],"investigate":[37],"two":[38],"different":[39],"approaches":[40,50],"for":[41],"enhancement":[43,115],"train":[45,52,78,93,118,157],"TTS":[46,80,94,159],"systems.":[47],"both":[49],"a":[53],"recursive":[54],"neural":[55],"network":[56],"(RNN)":[57],"map":[59],"acoustic":[60,81,95,154],"features":[61,67,89,134,155],"extracted":[62,126,138],"describing":[68],"speech.":[70,202],"enhanced":[72,132,185],"then":[75,150],"used":[76,151],"model.":[82],"one":[84],"approach":[85,166],"use":[87],"conventionally":[90],"employed":[91],"models,":[96],"i.e":[97],"Mel":[98],"cepstral":[99],"(MCEP)":[100],"coefficients,":[101],"aperiodicity":[102],"values":[103],"and":[104,135,192],"fundamental":[105],"frequency":[106],"(F0).":[107],"other":[110],"approach,":[111],"following":[112],"conventional":[113],"methods,":[116],"an":[119],"RNN":[120],"using":[121],"only":[122],"MCEP":[124,133,170],"coefficients":[125],"magnitude":[129],"spectrum.":[130],"phase":[137],"combined":[143],"reconstruct":[145],"waveform":[147],"which":[148],"extract":[153],"system.":[160],"We":[161],"show":[162],"that":[163,179],"second":[165],"results":[167],"in":[168],"larger":[169],"distortion":[171],"smaller":[173],"F0":[174],"errors.":[175],"Subjective":[176],"evaluation":[177],"shows":[178],"synthetic":[180],"trained":[182,199],"method":[188],"were":[189],"rated":[190],"higher":[191],"similar":[194],"scores":[196]},"counts_by_year":[{"year":2026,"cited_by_count":24},{"year":2025,"cited_by_count":83},{"year":2024,"cited_by_count":70},{"year":2023,"cited_by_count":65},{"year":2022,"cited_by_count":70},{"year":2021,"cited_by_count":58},{"year":2020,"cited_by_count":57},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}