{"id":"https://openalex.org/W2972489453","doi":"https://doi.org/10.21437/ssw.2019-40","title":"A Comparison of Letters and Phones as Input to Sequence-to-Sequence Models for Speech Synthesis","display_name":"A Comparison of Letters and Phones as Input to Sequence-to-Sequence Models for Speech Synthesis","publication_year":2019,"publication_date":"2019-09-14","ids":{"openalex":"https://openalex.org/W2972489453","doi":"https://doi.org/10.21437/ssw.2019-40","mag":"2972489453"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2019-40","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/72b6ef3f-f722-4a83-b487-e1f0703a4a66","any_repository_has_fulltext":true},"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":true,"raw_author_name":"Jason Fong","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"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/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 (CSTR), University of Edinburgh, UK"],"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/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"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":"Korin Richmond","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), 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":false,"raw_author_name":"Simon King","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043162691"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":1.6802,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88448272,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"223","last_page":"227"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"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":0.9954000115394592,"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/sequence","display_name":"Sequence (biology)","score":0.8344622850418091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6962524652481079},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.565646231174469},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34442687034606934},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.04717886447906494},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.037038177251815796}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.8344622850418091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6962524652481079},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.565646231174469},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34442687034606934},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.04717886447906494},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.037038177251815796}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/ssw.2019-40","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/72b6ef3f-f722-4a83-b487-e1f0703a4a66","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/72b6ef3f-f722-4a83-b487-e1f0703a4a66","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":"Fong, J, Taylor, J, Richmond, K & King, S 2019, A Comparison between Letters and Phones as Input to Sequence-to-Sequence Models for Speech Synthesis. in Proceedings of the 10th ISCA Speech Synthesis Workshop. International Speech Communication Association, pp. 223-227, The 10th ISCA Speech Synthesis Workshop, Vienna, Austria, 20/09/19. https://doi.org/10.21437/SSW.2019-40","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/72b6ef3f-f722-4a83-b487-e1f0703a4a66","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/72b6ef3f-f722-4a83-b487-e1f0703a4a66","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/72b6ef3f-f722-4a83-b487-e1f0703a4a66","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/72b6ef3f-f722-4a83-b487-e1f0703a4a66","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":"Fong, J, Taylor, J, Richmond, K & King, S 2019, A Comparison between Letters and Phones as Input to Sequence-to-Sequence Models for Speech Synthesis. in Proceedings of the 10th ISCA Speech Synthesis Workshop. International Speech Communication Association, pp. 223-227, The 10th ISCA Speech Synthesis Workshop, Vienna, Austria, 20/09/19. https://doi.org/10.21437/SSW.2019-40","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G275223502","display_name":null,"funder_award_id":"1939413","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"}],"funders":[{"id":"https://openalex.org/F4320334630","display_name":"Economic and Social Research Council","ror":"https://ror.org/03n0ht308"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1523135049","https://openalex.org/W1630569004","https://openalex.org/W1902237438","https://openalex.org/W2103085228","https://openalex.org/W2133564696","https://openalex.org/W2170980774","https://openalex.org/W2487675197","https://openalex.org/W2598638573","https://openalex.org/W2767052532","https://openalex.org/W2963212250","https://openalex.org/W2963609956","https://openalex.org/W2963827314","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972610613","https://openalex.org/W2972817752","https://openalex.org/W3144245117","https://openalex.org/W4394150413"],"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/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Neural":[0],"sequence-to-sequence":[1],"(S2S)":[2],"models":[3,71],"for":[4,16,162,203,228],"text-tospeech":[5],"synthesis":[6],"(TTS)":[7],"may":[8,89],"take":[9],"letter":[10],"or":[11],"phone":[12,36,98],"input":[13],"sequences.":[14],"Since":[15],"many":[17],"languages":[18],"phones":[19],"have":[20,154,176],"a":[21,87,109,121,187],"more":[22],"direct":[23],"relationship":[24],"to":[25,31,59,78,113,140,166,186,197,200,221,225],"the":[26,51,127,141,151,172,215,219,226],"acoustic":[27],"signal,":[28],"they":[29,208],"lead":[30],"improved":[32],"quality.":[33],"But":[34],"generating":[35],"transcriptions":[37,179],"from":[38],"text":[39],"requires":[40],"an":[41,45,75],"expensive":[42],"dictionary":[43,227],"and":[44,50,81],"error-prone":[46],"grapheme-to-phoneme":[47],"(G2P)":[48],"model,":[49],"relative":[52],"improvement":[53],"over":[54],"using":[55],"letters":[56],"has":[57],"yet":[58],"be":[60,91],"quantified.":[61],"In":[62],"approaching":[63],"this":[64,102,107],"question,":[65],"we":[66,104,159],"presume":[67],"that":[68,161],"letter-input":[69,110],"S2S":[70,95,111],"must":[72],"implicitly":[73],"learn":[74],"internal":[76],"counterpart":[77],"G2P":[79,199],"conversion":[80],"therefore":[82],"inevitably":[83],"make":[84],"errors.":[85],"Such":[86],"model":[88],"thus":[90],"viewed":[92],"as":[93],"phone-input":[94,115,142],"with":[96,120],"inaccurate":[97],"input.":[99],"To":[100],"quantify":[101],"inaccuracy,":[103],"compare":[105],"in":[106,126,138,144,150,171,184],"paper":[108],"system":[112,135,143],"several":[114],"systems":[116,164],"trained":[117],"on":[118],"data":[119,153,174],"varying":[122],"level":[123],"of":[124,147,168,214],"error":[125,189],"phonetic":[128,156,178],"transcription.":[129],"Our":[130],"findings":[131],"show":[132],"our":[133],"letterinput":[134],"is":[136,195],"equivalent":[137],"quality":[139],"which":[145],"25%":[146],"word":[148,169],"tokens":[149,170],"training":[152,173,216,231],"incorrect":[155,177],"transcriptions.":[157],"Furthermore,":[158],"find":[160],"phoneinput":[163],"up":[165],"15%":[167,213],"can":[175],"without":[180],"any":[181],"significant":[182],"difference":[183],"performance":[185],"0%":[188],"rate":[190],"system.":[191],"This":[192],"suggests":[193],"it":[194],"acceptable":[196],"use":[198],"predict":[201],"pronunciations":[202],"out-of-vocabulary":[204],"words":[205],"(OOVs)":[206],"provided":[207],"are":[209],"less":[210],"than":[211],"around":[212],"data,":[217],"removing":[218],"need":[220],"manually":[222],"add":[223],"OOVs":[224],"every":[229],"new":[230],"set.":[232]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
