{"id":"https://openalex.org/W2514457011","doi":"https://doi.org/10.18653/v1/p16-1038","title":"Grapheme-to-Phoneme Models for (Almost) Any Language","display_name":"Grapheme-to-Phoneme Models for (Almost) Any Language","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2514457011","doi":"https://doi.org/10.18653/v1/p16-1038","mag":"2514457011"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p16-1038","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1038","pdf_url":"https://www.aclweb.org/anthology/P16-1038.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 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P16-1038.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078199266","display_name":"Aliya Deri","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I903300897","display_name":"Southern States University","ror":"https://ror.org/01b0j0m34","country_code":"US","type":"education","lineage":["https://openalex.org/I903300897"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aliya Deri","raw_affiliation_strings":["Information Sciences Institute Department of Computer Science University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute Department of Computer Science University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I903300897"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106821597","display_name":"Kevin Knight","orcid":"https://orcid.org/0000-0001-9117-1718"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I903300897","display_name":"Southern States University","ror":"https://ror.org/01b0j0m34","country_code":"US","type":"education","lineage":["https://openalex.org/I903300897"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Knight","raw_affiliation_strings":["Information Sciences Institute Department of Computer Science University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute Department of Computer Science University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I903300897"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":49,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"399","last_page":"408"},"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":0.9986000061035156,"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":0.7673050761222839},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7281466722488403},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.607168972492218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4722259044647217},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.36552900075912476},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08184477686882019}],"concepts":[{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.7673050761222839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281466722488403},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.607168972492218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4722259044647217},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.36552900075912476},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08184477686882019},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p16-1038","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1038","pdf_url":"https://www.aclweb.org/anthology/P16-1038.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 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p16-1038","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1038","pdf_url":"https://www.aclweb.org/anthology/P16-1038.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 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8092615179","display_name":null,"funder_award_id":"HR0011-15-C-0115","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320308668","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2514457011.pdf","grobid_xml":"https://content.openalex.org/works/W2514457011.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W49690127","https://openalex.org/W101576916","https://openalex.org/W273093436","https://openalex.org/W609109566","https://openalex.org/W1567679865","https://openalex.org/W1594560709","https://openalex.org/W1990856848","https://openalex.org/W2084534958","https://openalex.org/W2098267481","https://openalex.org/W2106440210","https://openalex.org/W2114879013","https://openalex.org/W2251711535","https://openalex.org/W2252089152","https://openalex.org/W2293438896","https://openalex.org/W2397721308","https://openalex.org/W2399033582","https://openalex.org/W2402712980","https://openalex.org/W2916210361","https://openalex.org/W2916454001","https://openalex.org/W3166486483","https://openalex.org/W4300528752"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2060656088","https://openalex.org/W2506515307","https://openalex.org/W4385893898","https://openalex.org/W2383836440","https://openalex.org/W2610662399","https://openalex.org/W4285757703","https://openalex.org/W2509341624","https://openalex.org/W112480583","https://openalex.org/W2057468170"],"abstract_inverted_index":{"Grapheme-to-phoneme":[0],"(g2p)":[1],"models":[2,55,61,70],"are":[3],"rarely":[4],"available":[5],"in":[6,31],"low-resource":[7,64],"languages,":[8],"as":[9],"the":[10],"creation":[11],"of":[12],"training":[13],"and":[14,19,40,47],"evaluation":[15],"data":[16],"is":[17],"expensive":[18],"time-consuming.":[20],"We":[21,36,66],"use":[22],"Wiktionary":[23],"to":[24,59],"obtain":[25],"more":[26,32],"than":[27,33],"650k":[28],"word-pronunciation":[29],"pairs":[30],"500":[34],"languages.":[35,65,74],"then":[37],"develop":[38],"phoneme":[39],"language":[41],"distance":[42],"metrics":[43],"based":[44],"on":[45],"phonological":[46],"linguistic":[48],"knowledge;":[49],"applying":[50],"those,":[51],"we":[52],"adapt":[53],"g2p":[54],"for":[56,62,69,71],"highresource":[57],"languages":[58],"create":[60],"related":[63],"provide":[67],"results":[68],"229":[72],"adapted":[73]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}