{"id":"https://openalex.org/W3010788072","doi":"https://doi.org/10.1109/icassp40776.2020.9054557","title":"Joint Phoneme-Grapheme Model for End-To-End Speech Recognition","display_name":"Joint Phoneme-Grapheme Model for End-To-End Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3010788072","doi":"https://doi.org/10.1109/icassp40776.2020.9054557","mag":"3010788072"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054557","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":"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/A5102252420","display_name":"Yotaro Kubo","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210136457","display_name":"Shibuya (Japan)","ror":"https://ror.org/03t1ztz45","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210136457"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Yotaro Kubo","raw_affiliation_strings":["Google, Shibuya-ku, Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Shibuya-ku, Tokyo","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210136457"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210136457","display_name":"Shibuya (Japan)","ror":"https://ror.org/03t1ztz45","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210136457"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Michiel Bacchiani","raw_affiliation_strings":["Google, Shibuya-ku, Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Shibuya-ku, Tokyo","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210136457"]}]}],"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":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"6119","last_page":"6123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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":0.9987999796867371,"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":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.8585777282714844},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.7317309975624084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6591611504554749},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6089552044868469},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6024394035339355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.523490309715271},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5075985193252563},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4939165711402893},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4534849524497986},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43216684460639954},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4248828887939453},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4203088879585266},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3825249969959259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8585777282714844},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.7317309975624084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6591611504554749},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6089552044868469},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6024394035339355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.523490309715271},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5075985193252563},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4939165711402893},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4534849524497986},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43216684460639954},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4248828887939453},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4203088879585266},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3825249969959259},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054557","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":0.6000000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1629097610","https://openalex.org/W2064675550","https://openalex.org/W2133564696","https://openalex.org/W2137630452","https://openalex.org/W2327501763","https://openalex.org/W2750499125","https://openalex.org/W2752047430","https://openalex.org/W2913340405","https://openalex.org/W2962824709","https://openalex.org/W2963434219","https://openalex.org/W2963842982","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W6631190155","https://openalex.org/W6636899088","https://openalex.org/W6679434410","https://openalex.org/W6685145238","https://openalex.org/W6743726175"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"This":[0],"paper":[1,38],"proposes":[2],"methods":[3,16],"to":[4,22,58,86,92,131],"improve":[5,23],"a":[6,60,102,138,153,162,171],"commonly":[7],"used":[8],"end-to-end":[9],"speech":[10,69,167],"recognition":[11,73],"model,":[12],"Listen-Attend-Spell":[13],"(LAS).":[14],"The":[15,34,156],"we":[17,96],"propose":[18],"use":[19],"multi-task":[20,41,94,125,173],"learning":[21,126],"generalization":[24],"of":[25,63,67,84,165,170,179],"the":[26,51,64,68,81,114,180],"model":[27,140,182],"by":[28,100,152],"leveraging":[29],"information":[30],"from":[31],"multiple":[32],"labels.":[33],"focus":[35],"in":[36,110,135],"this":[37,136],"is":[39,141,150,159,175],"on":[40,144,161],"models":[42],"for":[43],"simultaneous":[44],"signal-to-grapheme":[45],"and":[46,118],"signal-to-phoneme":[47],"conversions":[48],"while":[49],"sharing":[50],"encoder":[52],"parameters.":[53],"Since":[54],"phonemes":[55,117],"are":[56,121,129],"designed":[57],"be":[59,87,132],"precise":[61],"description":[62],"linguistic":[65],"aspects":[66],"signal,":[70],"using":[71],"phoneme":[72],"as":[74],"an":[75],"auxiliary":[76],"task":[77],"can":[78,105],"help":[79],"guiding":[80],"early":[82],"stages":[83],"training":[85],"more":[88],"stable.":[89],"In":[90,123],"addition":[91],"conventional":[93,124,172],"learning,":[95],"obtain":[97],"further":[98],"improvements":[99],"introducing":[101],"method":[103,158],"that":[104,178],"exploit":[106],"dependencies":[107,115],"between":[108,116],"labels":[109],"different":[111],"tasks.":[112],"Specifically,":[113],"grapheme":[119],"sequences":[120,128],"considered.":[122],"these":[127],"assumed":[130],"independent.":[133],"Instead,":[134],"paper,":[137],"joint":[139,181],"proposed":[142,157],"based":[143],"\"iterative":[145],"refinement\"":[146],"where":[147],"dependency":[148],"modeling":[149],"achieved":[151],"multi-pass":[154],"strategy.":[155],"evaluated":[160],"28000h":[163],"corpus":[164],"Japanese":[166],"data.":[168],"Performance":[169],"approach":[174],"contrasted":[176],"with":[177,183],"iterative":[184],"refinement.":[185]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}