{"id":"https://openalex.org/W2972437137","doi":"https://doi.org/10.21437/interspeech.2019-1954","title":"Transformer Based Grapheme-to-Phoneme Conversion","display_name":"Transformer Based Grapheme-to-Phoneme Conversion","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972437137","doi":"https://doi.org/10.21437/interspeech.2019-1954","mag":"2972437137"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1954","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.06338","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039141375","display_name":"Sevinj Yolchuyeva","orcid":"https://orcid.org/0000-0001-6760-1546"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Sevinj Yolchuyeva","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069988513","display_name":"G\u00e9za N\u00e9meth","orcid":"https://orcid.org/0000-0002-2311-4858"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"G\u00e9za N\u00e9meth","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018247113","display_name":"B\u00e1lint Gyires-T\u00f3th","orcid":"https://orcid.org/0000-0003-1059-9822"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"B\u00e1lint Gyires-T\u00f3th","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039141375"],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":3.7565,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.9472833,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2095","last_page":"2099"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973000288009644,"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":0.9193324446678162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8430274128913879},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7933539152145386},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.688629150390625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6324699521064758},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5658039450645447},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.553077220916748},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5306364893913269},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5104376673698425},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4613914489746094},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34517812728881836},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0940750241279602}],"concepts":[{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.9193324446678162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8430274128913879},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7933539152145386},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.688629150390625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6324699521064758},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5658039450645447},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.553077220916748},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5306364893913269},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5104376673698425},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4613914489746094},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34517812728881836},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0940750241279602},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":3,"locations":[{"id":"doi:10.21437/interspeech.2019-1954","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:real.mtak.hu:101529","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400081","display_name":"Repository of the Academy's Library (Library of the Hungarian Academy of Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210140733","host_organization_name":"Library and Information Centre of the Hungarian Academy of Sciences","host_organization_lineage":["https://openalex.org/I4210140733"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:arXiv.org:2004.06338","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.06338","pdf_url":"https://arxiv.org/pdf/2004.06338","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.06338","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.06338","pdf_url":"https://arxiv.org/pdf/2004.06338","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W67332896","https://openalex.org/W312219375","https://openalex.org/W1522301498","https://openalex.org/W1647671624","https://openalex.org/W1779680350","https://openalex.org/W1916501714","https://openalex.org/W2090755665","https://openalex.org/W2095705004","https://openalex.org/W2130942839","https://openalex.org/W2163605009","https://openalex.org/W2517101095","https://openalex.org/W2538246917","https://openalex.org/W2552839021","https://openalex.org/W2591927543","https://openalex.org/W2608712415","https://openalex.org/W2748157908","https://openalex.org/W2800782462","https://openalex.org/W2809456172","https://openalex.org/W2884873108","https://openalex.org/W2889358390","https://openalex.org/W2920834369","https://openalex.org/W2963299674","https://openalex.org/W2963403868","https://openalex.org/W2963499433","https://openalex.org/W2963609956","https://openalex.org/W2963913768","https://openalex.org/W2964121744","https://openalex.org/W2964281804","https://openalex.org/W2972903407","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4388333509","https://openalex.org/W4287752972","https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W3037482713","https://openalex.org/W2903810591","https://openalex.org/W3026554633","https://openalex.org/W2888520903","https://openalex.org/W2890256614","https://openalex.org/W3037446006"],"abstract_inverted_index":{"Attention":[0],"mechanism":[1],"is":[2,38,144],"one":[3],"of":[4,68,114,140,150],"the":[5,66,92,98,109,138,141,148,151],"most":[6],"successful
\\ntechniques":[7],"in":[8,28,53,112],"deep":[9],"learning":[10],"based":[11,20,83,106],"Natural":[12],"Language
\\nProcessing":[13],"(NLP).":[14],"The":[15,101],"transformer":[16,69,105],"network":[17,82],"architecture":[18,70],"is
\\ncompletely":[19],"on":[21,91,134],"attention":[22],"mechanisms,":[23],"and":[24,33,56,74,97,118,130],"it
\\noutperforms":[25],"sequence-to-sequence":[26],"models":[27],"neural":[29,81],"machine
\\ntranslation":[30],"without":[31],"recurrent":[32,79,124],"convolutional":[34],"layers.
\\nGrapheme-to-phoneme":[35],"(G2P)":[36],"conversion":[37,73],"a":[39,51],"task":[40],"of
\\nconverting":[41],"letters":[42],"(grapheme":[43],"sequence)":[44],"to":[45,71],"their
\\npronunciations":[46],"(phoneme":[47],"sequence).":[48],"It":[49],"plays":[50],"significant
\\nrole":[52],"text-to-speech":[54],"(TTS)":[55],"automatic":[57],"speech
\\nrecognition":[58],"(ASR)":[59],"systems.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64],"investigate":[65],"application":[67],"G2P":[72,107],"compare":[75],"its":[76],"performance":[77],"with":[78],"and
\\nconvolutional":[80],"approaches.":[84,153],"Phoneme
\\nand":[85],"word":[86,115,129],"error":[87,116,132],"rates":[88,133],"are":[89],"evaluated":[90],"CMUDict":[93],"dataset
\\nfor":[94],"US":[95],"English":[96],"NetTalk":[99],"dataset.":[100],"results":[102,120],"show":[103],"that":[104],"outperforms":[108],"convolutional-based":[110],"approach":[111],"terms":[113],"rate":[117],"our":[119],"significantly":[121],"exceeded":[122],"previous":[123,152],"approaches":[125],"(without":[126],"attention)":[127],"regarding":[128],"phoneme":[131],"both":[135],"datasets.":[136],"Furthermore,":[137],"size":[139,149],"proposed":[142],"model":[143],"much":[145],"smaller":[146],"than":[147]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}