{"id":"https://openalex.org/W3096232484","doi":"https://doi.org/10.21437/interspeech.2020-2618","title":"Testing the Limits of Representation Mixing for Pronunciation Correction in End-to-End Speech Synthesis","display_name":"Testing the Limits of Representation Mixing for Pronunciation Correction in End-to-End Speech Synthesis","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096232484","doi":"https://doi.org/10.21437/interspeech.2020-2618","mag":"3096232484"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2618","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","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/A5043162691","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, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080895440","display_name":"Jason R. Taylor","orcid":"https://orcid.org/0000-0002-7871-448X"},"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 Taylor","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","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":false,"raw_author_name":"Simon King","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4019","last_page":"4023"},"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":0.9987000226974487,"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":0.998199999332428,"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":0.669959545135498},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6544374227523804},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5960414409637451},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5755432844161987},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4864377975463867},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.4486883580684662},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41896456480026245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3594517707824707},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3333834707736969},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20766785740852356},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09721723198890686}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.669959545135498},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6544374227523804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5960414409637451},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5755432844161987},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4864377975463867},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.4486883580684662},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41896456480026245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3594517707824707},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3333834707736969},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20766785740852356},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09721723198890686},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-2618","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/872c1d64-91c0-47da-95c5-e5cabf823c99","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/872c1d64-91c0-47da-95c5-e5cabf823c99","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":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1523135049","https://openalex.org/W2099954993","https://openalex.org/W2103085228","https://openalex.org/W2164107060","https://openalex.org/W2170980774","https://openalex.org/W2766812927","https://openalex.org/W2963609956","https://openalex.org/W2963827314","https://openalex.org/W2964243274","https://openalex.org/W3016160783","https://openalex.org/W3144245117","https://openalex.org/W4298580827","https://openalex.org/W4394150413"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W2776838583","https://openalex.org/W2359469050","https://openalex.org/W1607396156"],"abstract_inverted_index":{"Accurate":[0],"pronunciation":[1,15,41,83,103],"is":[2,30,85,91,155],"an":[3,25,106],"essential":[4],"requirement":[5],"for":[6],"textto-speech":[7],"(TTS)":[8],"systems.Systems":[9],"trained":[10],"on":[11],"raw":[12],"text":[13],"exhibit":[14],"errors":[16,84,104],"in":[17,74,105],"output":[18],"speech":[19,165],"due":[20],"to":[21,32,44,61,101,134],"ambiguous":[22],"letterto-sound":[23],"relations.Without":[24],"intermediate":[26],"phonemic":[27,70,126],"representation,":[28],"it":[29],"difficult":[31],"intervene":[33],"and":[34],"correct":[35,102],"these":[36],"errors.Retaining":[37],"explicit":[38],"control":[39,149],"over":[40,150],"runs":[42],"counter":[43],"the":[45,55,77,94,120,163,172],"current":[46],"drive":[47],"toward":[48],"end-to-end":[49],"(E2E)":[50],"TTS":[51,59,109],"using":[52],"sequence-tosequence":[53],"models.On":[54],"one":[56],"hand,":[57],"E2E":[58,108],"aims":[60],"eliminate":[62],"manual":[63],"intervention,":[64],"especially":[65],"expert":[66],"skill":[67],"such":[68],"as":[69],"transcription":[71],"of":[72,86,97,174],"words":[73],"a":[75,79,142],"lexicon.On":[76],"other,":[78],"system":[80,110,121],"making":[81],"difficult-to-correct":[82],"little":[87,130],"practical":[88],"use.Some":[89],"intervention":[90],"necessary.We":[92],"explore":[93],"minimal":[95],"amount":[96],"linguistic":[98],"features":[99],"required":[100],"otherwise":[107],"that":[111],"accepts":[112,122],"graphemic":[113,124],"input.We":[114,127],"use":[115],"representation-mixing:":[116],"within":[117],"each":[118],"sequence":[119],"either":[123],"and/or":[125],"quantify":[128],"how":[129,140],"training":[131],"data":[132],"needs":[133],"be":[135,145],"phonemically":[136],"labelled":[137],"-that":[138],"is,":[139],"small":[141],"lexicon":[143],"must":[144],"written":[146],"-to":[147],"ensure":[148],"pronunciation.We":[151],"find":[152],"modest":[153],"correction":[154,168],"possible":[156],"with":[157,179],"500":[158],"phonemised":[159,178],"word":[160,175],"types":[161,176],"from":[162],"LJ":[164],"dataset":[166],"but":[167],"works":[169],"best":[170],"when":[171],"majority":[173],"are":[177],"syllable":[180],"boundaries.":[181]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}