{"id":"https://openalex.org/W3198848374","doi":"https://doi.org/10.21437/interspeech.2021-546","title":"T5G2P: Using Text-to-Text Transfer Transformer for Grapheme-to-Phoneme Conversion","display_name":"T5G2P: Using Text-to-Text Transfer Transformer for Grapheme-to-Phoneme Conversion","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198848374","doi":"https://doi.org/10.21437/interspeech.2021-546","mag":"3198848374"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-546","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5067919772","display_name":"Mark\u00e9ta \u0158ez\u00e1\u010dkov\u00e1","orcid":"https://orcid.org/0000-0002-6194-7826"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark\u00e9ta \u0158ez\u00e1\u010dkov\u00e1","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072542443","display_name":"J\u00e1n \u0160vec","orcid":"https://orcid.org/0000-0001-8362-5927"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan \u0160vec","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029012602","display_name":"Daniel Tihelka","orcid":"https://orcid.org/0000-0002-3149-2330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Tihelka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2389,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90082148,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.8566672801971436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7650009989738464},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6944781541824341},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5116294026374817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45919692516326904},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37616872787475586},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11299067735671997},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08458811044692993},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07556918263435364},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07103228569030762}],"concepts":[{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.8566672801971436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7650009989738464},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6944781541824341},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5116294026374817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45919692516326904},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37616872787475586},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11299067735671997},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08458811044692993},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07556918263435364},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07103228569030762},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-546","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace5.zcu.cz:11025/47249","is_oa":false,"landing_page_url":"http://hdl.handle.net/11025/47249","pdf_url":null,"source":{"id":"https://openalex.org/S4306400586","display_name":"Digital Library (University of West Bohemia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I92715842","host_organization_name":"University of West Bohemia in Pilsen","host_organization_lineage":["https://openalex.org/I92715842"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"konferen\u010dn\u00ed p\u0159\u00edsp\u011bvek"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1593247906","https://openalex.org/W1916501714","https://openalex.org/W2157331557","https://openalex.org/W2525778437","https://openalex.org/W2901997113","https://openalex.org/W2972437137","https://openalex.org/W3098824823","https://openalex.org/W3130016944","https://openalex.org/W3144192465"],"related_works":["https://openalex.org/W4287752972","https://openalex.org/W3037446006","https://openalex.org/W3037482713","https://openalex.org/W2789919619","https://openalex.org/W2293457016","https://openalex.org/W3150282468","https://openalex.org/W4221155853","https://openalex.org/W3169305685","https://openalex.org/W2758964148","https://openalex.org/W2148450754"],"abstract_inverted_index":{"Despite":[0],"the":[1,9,113],"increasing":[2],"popularity":[3],"of":[4,19,62,80,90,98,115],"end-to-end":[5],"text-to-speech":[6],"(TTS)":[7],"systems,":[8],"correct":[10],"grapheme-to-phoneme":[11],"(G2P)":[12],"module":[13],"is":[14,44,67],"still":[15],"a":[16,23,32,35,53,57,99],"crucial":[17],"part":[18],"those":[20],"relying":[21],"on":[22,70],"phonetic":[24,110],"input.":[25],"In":[26],"this":[27],"paper,":[28],"we,":[29],"therefore,":[30],"introduce":[31],"T5G2P":[33],"model,":[34],"Text-to-Text":[36],"Transfer":[37],"Transformer":[38],"(T5)":[39],"neural":[40],"network":[41],"model":[42,66],"which":[43],"able":[45],"to":[46,108],"convert":[47],"an":[48,96],"input":[49],"text":[50],"sentence":[51],"into":[52],"phoneme":[54],"sequence":[55],"with":[56],"high":[58],"accuracy.":[59],"The":[60,92],"evaluation":[61],"our":[63],"trained":[64],"T5":[65],"carried":[68],"out":[69],"English":[71,103],"and":[72,87,104],"Czech,":[73],"since":[74],"there":[75],"are":[76],"different":[77],"specific":[78],"properties":[79],"G2P,":[81],"including":[82],"homograph":[83],"disambiguation,":[84],"cross-word":[85],"assimilation":[86],"irregular":[88],"pronunciation":[89,116],"loanwords.":[91],"paper":[93],"also":[94],"contains":[95],"analysis":[97],"homographs":[100],"issue":[101],"in":[102],"offers":[105],"another":[106],"approach":[107],"Czech":[109],"transcription":[111],"using":[112],"detection":[114],"exceptions.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}