{"id":"https://openalex.org/W4296069123","doi":"https://doi.org/10.21437/interspeech.2022-10138","title":"Speech Audio Corrector: using speech from non-target speakers for one-off correction of mispronunciations in grapheme-input text-to-speech","display_name":"Speech Audio Corrector: using speech from non-target speakers for one-off correction of mispronunciations in grapheme-input text-to-speech","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069123","doi":"https://doi.org/10.21437/interspeech.2022-10138"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10138","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10138","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/cda025ee-e293-40f3-afb1-decd816d9847","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008374851","display_name":"Jason Fong","orcid":null},"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":"Jason Fong","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078393469","display_name":"Daniel Lyth","orcid":null},"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":"Daniel Lyth","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Gustav Eje Henter","raw_affiliation_strings":["Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662187","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2445-2605"},"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":"Hao Tang","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","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":true,"raw_author_name":"Simon King","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5062516688"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1213","last_page":"1217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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/T12031","display_name":"Speech and dialogue systems","score":0.9929999709129333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.9086685180664062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.811275064945221},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.7689892649650574},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7582919597625732},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7094818353652954},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5283967852592468},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5025560855865479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38916152715682983},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36074501276016235},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12137296795845032},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05904996395111084}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.9086685180664062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811275064945221},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.7689892649650574},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7582919597625732},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7094818353652954},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5283967852592468},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5025560855865479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38916152715682983},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36074501276016235},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12137296795845032},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05904996395111084},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2022-10138","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10138","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/cda025ee-e293-40f3-afb1-decd816d9847","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/cda025ee-e293-40f3-afb1-decd816d9847","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":null,"raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/cda025ee-e293-40f3-afb1-decd816d9847","is_oa":false,"landing_page_url":"https://www.isca-speech.org/archive/interspeech_2022/fong22_interspeech.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/cda025ee-e293-40f3-afb1-decd816d9847","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/cda025ee-e293-40f3-afb1-decd816d9847","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":null,"raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2150658333","https://openalex.org/W2747874407","https://openalex.org/W2763110165","https://openalex.org/W2767052532","https://openalex.org/W2884607399","https://openalex.org/W2903739847","https://openalex.org/W2933138175","https://openalex.org/W2963799213","https://openalex.org/W2963827314","https://openalex.org/W2964243274","https://openalex.org/W2972610613","https://openalex.org/W2997819339","https://openalex.org/W3024605872","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3096232484","https://openalex.org/W3140429000","https://openalex.org/W3150435369","https://openalex.org/W3169320628","https://openalex.org/W3180374548","https://openalex.org/W3197324626","https://openalex.org/W3197580070","https://openalex.org/W4214968481","https://openalex.org/W4286984129","https://openalex.org/W4287854499","https://openalex.org/W4287887366","https://openalex.org/W4288107125","https://openalex.org/W4394671563"],"related_works":["https://openalex.org/W2506515307","https://openalex.org/W2060656088","https://openalex.org/W2183593636","https://openalex.org/W117063597","https://openalex.org/W4289544804","https://openalex.org/W3031252497","https://openalex.org/W2080578089","https://openalex.org/W2179005426","https://openalex.org/W1982818675","https://openalex.org/W2605000190"],"abstract_inverted_index":{"Correct":[0],"pronunciation":[1,26,56,131],"is":[2],"essential":[3],"for":[4],"text-to-speech":[5],"(TTS)":[6],"systems":[7,12],"in":[8,45,90,112,126],"production.":[9],"Most":[10],"production":[11],"rely":[13],"on":[14],"pronouncing":[15],"dictionaries":[16,37,132],"to":[17,40,123],"perform":[18],"grapheme-to-phoneme":[19],"conversion.":[20],"Unlike":[21],"end-to-end":[22],"TTS,":[23],"this":[24],"enables":[25,107],"correction":[27,109],"by":[28,81],"manually":[29],"altering":[30],"the":[31,35,121],"phoneme":[32],"sequence,":[33],"but":[34],"necessary":[36],"are":[38,133],"labour-intensive":[39],"create":[41],"and":[42,94,128],"only":[43],"exist":[44],"a":[46,62,83,88,91],"few":[47],"high-resourced":[48],"languages.":[49],"This":[50,119],"work":[51],"demonstrates":[52],"that":[53,67,102],"accurate":[54],"TTS":[55,114,125],"control":[57,69],"can":[58,70],"be":[59,71],"achieved":[60],"without":[61,73],"dictionary.":[63],"Moreover,":[64],"we":[65],"show":[66,101],"such":[68],"performed":[72],"requiring":[74],"any":[75],"model":[76],"retraining":[77],"or":[78],"fine-tuning,":[79],"merely":[80],"supplying":[82],"single":[84],"correctly-pronounced":[85],"reading":[86],"of":[87,110],"word":[89],"different":[92],"voice":[93],"accent":[95],"at":[96],"synthesis":[97,117],"time.":[98],"Experimental":[99],"results":[100],"our":[103],"proposed":[104],"system":[105],"successfully":[106],"one-off":[108],"mispronunciations":[111],"grapheme-based":[113],"with":[115],"maintained":[116],"quality.":[118],"opens":[120],"door":[122],"production-level":[124],"languages":[127],"applications":[129],"where":[130],"unavailable.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}