{"id":"https://openalex.org/W4392911117","doi":"https://doi.org/10.1109/icassp48485.2024.10448105","title":"G2PU: Grapheme-To-Phoneme Transducer with Speech Units","display_name":"G2PU: Grapheme-To-Phoneme Transducer with Speech Units","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392911117","doi":"https://doi.org/10.1109/icassp48485.2024.10448105"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5080011047","display_name":"Heting Gao","orcid":"https://orcid.org/0000-0002-2857-3842"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heting Gao","raw_affiliation_strings":["University of Illinois at Urbana-Champaign (UIUC),USA","University of Illinois at Urbana-Champaign (UIUC), USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign (UIUC),USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign (UIUC), USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois at Urbana-Champaign (UIUC),USA","University of Illinois at Urbana-Champaign (UIUC), USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign (UIUC),USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign (UIUC), USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073287748","display_name":"Chang D. Yoo","orcid":"https://orcid.org/0000-0002-0756-7179"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang D. Yoo","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),Korean","Korea Advanced Institute of Science and Technology (KAIST), Korean"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),Korean","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST), Korean","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10061","last_page":"10065"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9948999881744385,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9948999881744385,"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/T12031","display_name":"Speech and dialogue systems","score":0.9854000210762024,"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":0.9484000205993652,"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":0.9048581123352051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6834877729415894},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.6500399708747864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5896356105804443},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2789447009563446},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12975284457206726},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06196072697639465}],"concepts":[{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.9048581123352051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6834877729415894},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.6500399708747864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5896356105804443},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2789447009563446},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12975284457206726},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06196072697639465},{"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:10.1109/icassp48485.2024.10448105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2526425061","https://openalex.org/W2747874407","https://openalex.org/W2894835365","https://openalex.org/W2896457183","https://openalex.org/W2963431393","https://openalex.org/W2965373594","https://openalex.org/W2972457126","https://openalex.org/W3036601975","https://openalex.org/W3088761213","https://openalex.org/W3095732712","https://openalex.org/W3095762785","https://openalex.org/W3140429000","https://openalex.org/W3161669994","https://openalex.org/W3197278374","https://openalex.org/W3197792608","https://openalex.org/W3198533616","https://openalex.org/W3198848374","https://openalex.org/W3209059054","https://openalex.org/W4224629880","https://openalex.org/W4287173589","https://openalex.org/W4296068408","https://openalex.org/W4297841354","https://openalex.org/W4394671563","https://openalex.org/W6755207826","https://openalex.org/W6779469704","https://openalex.org/W6780218876","https://openalex.org/W6790356757","https://openalex.org/W6795952400","https://openalex.org/W6839738141","https://openalex.org/W6946304369"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2506515307","https://openalex.org/W2060656088","https://openalex.org/W4385893898","https://openalex.org/W4285757703","https://openalex.org/W2383836440","https://openalex.org/W2610662399","https://openalex.org/W2509341624","https://openalex.org/W2057468170"],"abstract_inverted_index":{"Most":[0],"phoneme":[1,21,158,176],"transcripts":[2,159],"are":[3,24,81,116],"generated":[4,160],"using":[5,30,118,157],"forced":[6,107],"alignment:":[7],"typically":[8],"a":[9,54,62,136,162],"grapheme-to-phoneme":[10],"transducer":[11],"(G2P)":[12],"is":[13,155],"applied":[14],"to":[15,18,27,53,128,181,185,193],"text":[16,145],"sequences":[17],"generate":[19],"candidate":[20],"transcripts,":[22],"which":[23],"then":[25],"time-aligned":[26],"the":[28,38,44,46,50,79,88,112,147,197],"waveform":[29],"an":[31,68,73],"acoustic":[32,47,51],"model.":[33],"This":[34],"paper":[35],"demonstrates,":[36],"for":[37],"first":[39],"time,":[40],"simultaneous":[41],"optimization":[42],"of":[43,67,102,149],"G2P,":[45],"model,":[48],"and":[49,72,90,106,114,121,170],"alignment":[52,108],"corpus.":[55],"To":[56],"this":[57],"end,":[58],"we":[59,133,189],"propose":[60],"G2PU,":[61],"joint":[63],"CTC-attention":[64],"model":[65,154],"consisting":[66],"encoder-decoder":[69],"G2P":[70,89,105,113,164],"network":[71,139],"encoder-CTC":[74],"unit-to-phoneme":[75],"(U2P)":[76],"network,":[77],"where":[78],"units":[80,143],"extracted":[82],"from":[83,144],"speech.":[84,151],"We":[85],"demonstrate":[86],"that":[87,140,173],"U2P,":[91],"operating":[92],"in":[93,146],"parallel,":[94],"produce":[95],"lower":[96],"phone":[97],"error":[98,177],"rates":[99],"than":[100],"those":[101],"state-of-the-art":[103],"open-source":[104],"systems.":[109],"Furthermore,":[110],"although":[111],"U2P":[115],"trained":[117,156],"parallel":[119,150],"speech":[120,142],"text,":[122],"their":[123],"synergy":[124],"can":[125],"be":[126],"generalized":[127],"text-only":[129],"test":[130],"corpora":[131],"if":[132],"also":[134],"train":[135],"grapheme-to-unit":[137],"(G2U)":[138],"generates":[141],"absence":[148],"Our":[152,166],"G2PU":[153,174],"by":[161,179],"teacher":[163],"tool.":[165],"experiments":[167],"on":[168],"Chinese":[169],"Japanese":[171],"show":[172],"reduces":[175],"rate":[178],"7%":[180],"29%":[182],"relative":[183],"compared":[184],"its":[186],"teacher.":[187],"Finally,":[188],"include":[190],"case":[191],"studies":[192],"provide":[194],"insights":[195],"into":[196],"system\u2019s":[198],"workings.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}