{"id":"https://openalex.org/W3011874709","doi":"https://doi.org/10.1109/icassp40776.2020.9054696","title":"Multilingual Grapheme-To-Phoneme Conversion with Byte Representation","display_name":"Multilingual Grapheme-To-Phoneme Conversion with Byte Representation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3011874709","doi":"https://doi.org/10.1109/icassp40776.2020.9054696","mag":"3011874709"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5023072593","display_name":"Mingzhi Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mingzhi Yu","raw_affiliation_strings":["University of Pittsburgh"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101663835","display_name":"Hieu Duy Nguyen","orcid":"https://orcid.org/0000-0002-8774-5122"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hieu Duy Nguyen","raw_affiliation_strings":["Amazon.com Inc., USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com Inc., USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077849031","display_name":"Alex Sokolov","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Sokolov","raw_affiliation_strings":["Amazon.com Inc., USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com Inc., USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080058669","display_name":"Jack Lepird","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Lepird","raw_affiliation_strings":["Amazon.com Inc., USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com Inc., USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084035667","display_name":"Kanthashree Mysore Sathyendra","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kanthashree Mysore Sathyendra","raw_affiliation_strings":["Amazon.com Inc., USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com Inc., USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067594311","display_name":"Samridhi Choudhary","orcid":"https://orcid.org/0000-0003-3706-7260"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samridhi Choudhary","raw_affiliation_strings":["Amazon.com Inc., USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com Inc., USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029573067","display_name":"Athanasios Mouchtaris","orcid":"https://orcid.org/0000-0001-7583-0189"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Athanasios Mouchtaris","raw_affiliation_strings":["Amazon.com Inc., USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com Inc., USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074068808","display_name":"Siegfried Kunzmann","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siegfried Kunzmann","raw_affiliation_strings":["Amazon.com Inc., USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com Inc., USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5023072593"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":1.193,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.83123027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8234","last_page":"8238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9409828186035156},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.866602897644043},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8504859209060669},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6178592443466187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5401827692985535},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4678801894187927},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4357254207134247},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41128429770469666},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14823615550994873}],"concepts":[{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.9409828186035156},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.866602897644043},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8504859209060669},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6178592443466187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5401827692985535},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4678801894187927},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4357254207134247},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41128429770469666},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14823615550994873},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W120415783","https://openalex.org/W1593247906","https://openalex.org/W2040064907","https://openalex.org/W2090755665","https://openalex.org/W2251711535","https://openalex.org/W2514457011","https://openalex.org/W2748157908","https://openalex.org/W2778814079","https://openalex.org/W2805993470","https://openalex.org/W2963208801","https://openalex.org/W2963299674","https://openalex.org/W2963347649","https://openalex.org/W2963403868","https://openalex.org/W2963913768","https://openalex.org/W2964002616","https://openalex.org/W2972677740","https://openalex.org/W2972903407","https://openalex.org/W3082674894","https://openalex.org/W4385245566","https://openalex.org/W6604962579","https://openalex.org/W6639972086","https://openalex.org/W6691575401","https://openalex.org/W6739901393","https://openalex.org/W6746857927","https://openalex.org/W6752124048"],"related_works":["https://openalex.org/W2506515307","https://openalex.org/W2060656088","https://openalex.org/W4385893898","https://openalex.org/W2383836440","https://openalex.org/W2610662399","https://openalex.org/W4285757703","https://openalex.org/W2509341624","https://openalex.org/W2057468170","https://openalex.org/W112480583","https://openalex.org/W3011874709"],"abstract_inverted_index":{"Grapheme-to-phoneme":[0],"(G2P)":[1],"models":[2,139],"convert":[3],"a":[4,77],"written":[5],"word":[6,123],"into":[7],"its":[8],"corresponding":[9],"pronunciation":[10],"and":[11,17,34,65,103,111,132],"are":[12,140],"essential":[13],"components":[14],"in":[15,143],"automatic-speech-recognition":[16],"text-to-speech":[18],"systems.":[19],"Recently,":[20],"the":[21,98],"use":[22,134],"of":[23,45,100],"neural":[24],"encoder-decoder":[25],"architectures":[26],"has":[27],"substantially":[28],"improved":[29],"G2P":[30,40,56,79,105,156],"accuracy":[31],"for":[32,57,130,154],"mono-":[33,131],"multi-lingual":[35,133],"cases.":[36,135],"However,":[37],"most":[38],"multilingual":[39,78,155],"studies":[41],"focus":[42],"on":[43],"sets":[44],"languages":[46,58,158],"that":[47,148],"share":[48],"similar":[49],"graphemes,":[50],"such":[51],"as":[52],"European":[53,64,110],"languages.":[54],"Multilingual":[55],"from":[59,108],"different":[60,87],"writing":[61],"systems,":[62,89],"e.g.":[63],"East":[66,112],"Asian,":[67],"remains":[68],"an":[69,92,151],"understudied":[70],"area.":[71],"In":[72,136],"this":[73],"work,":[74],"we":[75],"propose":[76],"model":[80],"with":[81,91,157],"byte-level":[82,104,138],"input":[83],"representation":[84,118,153],"to":[85],"accommodate":[86],"grapheme":[88,161],"along":[90],"attention-based":[93],"Transformer":[94],"architecture.":[95],"We":[96],"evaluate":[97],"performance":[99],"both":[101],"character-level":[102],"using":[106,116],"data":[107],"multiple":[109],"Asian":[113],"locales.":[114],"Models":[115],"byte":[117,149],"yield":[119],"16.2%\u2013":[120],"50.2%":[121],"relative":[122],"error":[124],"rate":[125],"improvement":[126],"over":[127],"character-based":[128],"counterparts":[129],"addition,":[137],"15.0%\u201320.1%":[141],"smaller":[142],"size.":[144],"Our":[145],"results":[146],"show":[147],"is":[150],"efficient":[152],"having":[159],"large":[160],"vocabularies.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}