{"id":"https://openalex.org/W3037446006","doi":"https://doi.org/10.18653/v1/2020.sigmorphon-1.16","title":"One Model to Pronounce Them All: Multilingual Grapheme-to-Phoneme Conversion With a Transformer Ensemble","display_name":"One Model to Pronounce Them All: Multilingual Grapheme-to-Phoneme Conversion With a Transformer Ensemble","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3037446006","doi":"https://doi.org/10.18653/v1/2020.sigmorphon-1.16","mag":"3037446006"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.sigmorphon-1.16","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.sigmorphon-1.16","pdf_url":"https://www.aclweb.org/anthology/2020.sigmorphon-1.16.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/2020.sigmorphon-1.16.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003773150","display_name":"Kaili Vesik","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kaili Vesik","raw_affiliation_strings":["Department of Linguistics","Natural Language Processing Lab","The University of British Columbia ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics","institution_ids":[]},{"raw_affiliation_string":"Natural Language Processing Lab","institution_ids":[]},{"raw_affiliation_string":"The University of British Columbia ,","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004629670","display_name":"Muhammad Abdul-Mageed","orcid":"https://orcid.org/0000-0002-8590-2040"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Muhammad Abdul-Mageed","raw_affiliation_strings":["The University of British Columbia ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of British Columbia ,","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027026724","display_name":"Miikka Silfverberg","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Miikka Silfverberg","raw_affiliation_strings":["Department of Linguistics","The University of British Columbia ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics","institution_ids":[]},{"raw_affiliation_string":"The University of British Columbia ,","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9379554390907288},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.830324113368988},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8026375770568848},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7185766696929932},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6125142574310303},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5122563242912292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4947778582572937},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4928727149963379},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49106526374816895},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4122082591056824},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05431130528450012},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.053234755992889404}],"concepts":[{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.9379554390907288},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.830324113368988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8026375770568848},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7185766696929932},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6125142574310303},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5122563242912292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4947778582572937},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4928727149963379},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49106526374816895},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4122082591056824},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05431130528450012},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.053234755992889404},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2020.sigmorphon-1.16","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.sigmorphon-1.16","pdf_url":"https://www.aclweb.org/anthology/2020.sigmorphon-1.16.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2006.13343","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.13343","pdf_url":"https://arxiv.org/pdf/2006.13343","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"},{"id":"mag:3037446006","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.13343.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2006.13343","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.13343","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.sigmorphon-1.16","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.sigmorphon-1.16","pdf_url":"https://www.aclweb.org/anthology/2020.sigmorphon-1.16.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320334617","display_name":"Social Sciences and Humanities Research Council of Canada","ror":"https://ror.org/04j5jqy92"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3037446006.pdf","grobid_xml":"https://content.openalex.org/works/W3037446006.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2251743902","https://openalex.org/W2262393948","https://openalex.org/W2884873108","https://openalex.org/W2889358390","https://openalex.org/W2920834369","https://openalex.org/W2926840633","https://openalex.org/W2963212250","https://openalex.org/W2963247703","https://openalex.org/W3037676302"],"related_works":["https://openalex.org/W3037482713","https://openalex.org/W3037551631","https://openalex.org/W3185515067","https://openalex.org/W2963913768","https://openalex.org/W3198800856","https://openalex.org/W2113528982","https://openalex.org/W2983833314","https://openalex.org/W3196667351","https://openalex.org/W3049269430","https://openalex.org/W3114972750","https://openalex.org/W2401271578","https://openalex.org/W2405860391","https://openalex.org/W2786638153","https://openalex.org/W2210465651","https://openalex.org/W94373408","https://openalex.org/W2400639341","https://openalex.org/W2887191217","https://openalex.org/W2946445149","https://openalex.org/W2922328259","https://openalex.org/W3010788072"],"abstract_inverted_index":{"The":[0],"task":[1,102],"of":[2,42,68],"grapheme-to-phoneme":[3],"(G2P)":[4],"conversion":[5],"is":[6,35],"important":[7],"for":[8,59],"both":[9],"speech":[10,17],"recognition":[11],"and":[12,18,50,90],"synthesis.":[13],"Similar":[14],"to":[15,52],"other":[16],"language":[19],"processing":[20],"tasks,":[21],"in":[22,71],"a":[23,39,54,96],"scenario":[24],"where":[25],"only":[26],"small-sized":[27],"training":[28],"data":[29],"are":[30,64],"available,":[31],"learning":[32],"G2P":[33,57],"models":[34,63,83],"challenging.":[36],"We":[37],"describe":[38],"simple":[40],"approach":[41],"exploiting":[43],"model":[44],"ensembles,":[45],"based":[46],"on":[47],"multilingual":[48],"Transformers":[49],"self-training,":[51],"develop":[53],"highly":[55],"effective":[56],"solution":[58],"15":[60],"languages.":[61],"Our":[62,81],"developed":[65],"as":[66],"part":[67],"our":[69],"participation":[70],"the":[72,100],"SIGMORPHON":[73],"2020":[74],"Shared":[75],"Task":[76],"1":[77],"focused":[78],"at":[79],"G2P.":[80],"best":[82],"achieve":[84],"14.99":[85],"word":[86],"error":[87,93],"rate":[88,94],"(WER)":[89],"3.30":[91],"phoneme":[92],"(PER),":[95],"sizeable":[97],"improvement":[98],"over":[99],"shared":[101],"competitive":[103],"baselines.":[104]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}