{"id":"https://openalex.org/W4372266720","doi":"https://doi.org/10.1109/icassp49357.2023.10095249","title":"JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition","display_name":"JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266720","doi":"https://doi.org/10.1109/icassp49357.2023.10095249"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432591","display_name":"Weiran Wang","orcid":"https://orcid.org/0009-0000-0843-707X"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiran Wang","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032640894","display_name":"Rohit Prabhavalkar","orcid":"https://orcid.org/0000-0001-5331-6058"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohit Prabhavalkar","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076026485","display_name":"Tongzhou Chen","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tongzhou Chen","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040131037","display_name":"Ehsan Variani","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ehsan Variani","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374448","display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-6711-3603"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024773539","display_name":"Andrew Rosenberg","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5101749753"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.3986,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84484542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9955999851226807,"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":0.7616915702819824},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6086192727088928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4966769814491272},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.4435999393463135},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4377746880054474},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2371395230293274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7616915702819824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6086192727088928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4966769814491272},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.4435999393463135},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4377746880054474},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2371395230293274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1915251500","https://openalex.org/W1922655562","https://openalex.org/W1965555277","https://openalex.org/W2013598660","https://openalex.org/W2033256038","https://openalex.org/W2121879602","https://openalex.org/W2507771204","https://openalex.org/W2515801922","https://openalex.org/W2617258110","https://openalex.org/W2936774411","https://openalex.org/W2962824709","https://openalex.org/W2963747784","https://openalex.org/W2972625221","https://openalex.org/W2987019345","https://openalex.org/W3008037978","https://openalex.org/W3008181812","https://openalex.org/W3008480565","https://openalex.org/W3015194534","https://openalex.org/W3015686596","https://openalex.org/W3016234571","https://openalex.org/W3028545098","https://openalex.org/W3094667432","https://openalex.org/W3152221657","https://openalex.org/W3163203022","https://openalex.org/W3163560333","https://openalex.org/W3163605596","https://openalex.org/W3184976814","https://openalex.org/W3193461931","https://openalex.org/W3197507772","https://openalex.org/W3197661863","https://openalex.org/W3197976839","https://openalex.org/W3198442913","https://openalex.org/W3202419788","https://openalex.org/W3205788551","https://openalex.org/W3207222250","https://openalex.org/W4223622550","https://openalex.org/W4223988178","https://openalex.org/W4225319488","https://openalex.org/W4226120743","https://openalex.org/W4319862418","https://openalex.org/W4319862474","https://openalex.org/W6640059789","https://openalex.org/W6640090968","https://openalex.org/W6770245836","https://openalex.org/W6803092890"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"We":[0,104],"propose":[1,141],"JEIT,":[2,31,68],"a":[3,46,59,90,142,166,185],"joint":[4],"end-to-end":[5],"(E2E)":[6],"model":[7,11,34,54,186],"and":[8,64,94,121,145,157,162],"internal":[9],"language":[10],"(ILM)":[12],"training":[13,24,78,147],"method":[14],"to":[15,57,182],"inject":[16],"large-scale":[17],"unpaired":[18,50,73,136,173,189],"text":[19,74,137,155],"into":[20],"ILM":[21,44,65,69,83,129,158],"during":[22,128],"E2E":[23,33,37,53,63,77],"which":[25],"improves":[26,176],"rare-word":[27,177],"speech":[28],"recognition.":[29],"With":[30,171],"the":[32,76,96,118,133],"computes":[35],"an":[36],"loss":[38,48],"on":[39,49],"audio-transcript":[40],"pairs":[41],"while":[42,75],"its":[43],"estimates":[45],"cross-entropy":[47],"text.":[51,190],"The":[52],"is":[55,122],"trained":[56,187],"minimize":[58],"weighted":[60],"sum":[61],"of":[62,102,135],"losses.":[66],"During":[67],"absorbs":[70],"knowledge":[71],"from":[72,151],"serves":[79],"as":[80],"regularization.":[81],"Unlike":[82],"adaptation":[84,92],"methods,":[85],"JEIT":[86,119,144,161],"does":[87],"not":[88],"require":[89],"separate":[91],"step":[93],"avoids":[95],"need":[97],"for":[98],"Kullback-Leibler":[99],"divergence":[100],"regularization":[101],"ILM.":[103],"also":[105],"show":[106],"that":[107,149],"modular":[108],"hybrid":[109],"autoregressive":[110],"transducer":[111],"(MHAT)":[112],"performs":[113],"better":[114],"than":[115,126],"HAT":[116,127],"in":[117],"framework,":[120],"much":[123],"more":[124,167],"robust":[125],"adaptation.":[130],"To":[131],"push":[132],"limit":[134],"injection,":[138],"we":[139],"further":[140],"combined":[143],"JOIST":[146],"(CJJT)":[148],"benefits":[150],"modality":[152],"matching,":[153],"encoder":[154],"injection":[156],"training.":[159],"Both":[160],"CJJT":[163],"can":[164],"foster":[165],"effective":[168],"LM":[169],"fusion.":[170],"100B":[172],"sentences,":[174],"JEIT/CJJT":[175],"recognition":[178],"accuracy":[179],"by":[180],"up":[181],"16.4%":[183],"over":[184],"without":[188]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}