{"id":"https://openalex.org/W4319862712","doi":"https://doi.org/10.1109/slt54892.2023.10023028","title":"Scaling Up Deliberation For Multilingual ASR","display_name":"Scaling Up Deliberation For Multilingual ASR","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862712","doi":"https://doi.org/10.1109/slt54892.2023.10023028"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023028","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5029338576","display_name":"Ke Hu","orcid":"https://orcid.org/0000-0002-1599-1519"},"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":"Ke Hu","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"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"],"raw_orcid":null,"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/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"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.6534,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65262162,"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":"771","last_page":"776"},"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/deliberation","display_name":"Deliberation","score":0.9134079217910767},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8082237839698792},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6394460797309875},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5304517149925232},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5251892805099487},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.475616991519928},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42803773283958435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4204332232475281},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41384631395339966},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10903897881507874}],"concepts":[{"id":"https://openalex.org/C2776946740","wikidata":"https://www.wikidata.org/wiki/Q358652","display_name":"Deliberation","level":3,"score":0.9134079217910767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082237839698792},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6394460797309875},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5304517149925232},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5251892805099487},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.475616991519928},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42803773283958435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4204332232475281},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41384631395339966},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10903897881507874},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023028","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6000000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2086161653","https://openalex.org/W2226734577","https://openalex.org/W2752047430","https://openalex.org/W2786835190","https://openalex.org/W2808640845","https://openalex.org/W2928941594","https://openalex.org/W2936774411","https://openalex.org/W2953384591","https://openalex.org/W2962704885","https://openalex.org/W2963240019","https://openalex.org/W2963431393","https://openalex.org/W2971840980","https://openalex.org/W2973122799","https://openalex.org/W3011339933","https://openalex.org/W3015506840","https://openalex.org/W3095994005","https://openalex.org/W3096032230","https://openalex.org/W3096215352","https://openalex.org/W3097338456","https://openalex.org/W3097777922","https://openalex.org/W3141464856","https://openalex.org/W3163203022","https://openalex.org/W3178647810","https://openalex.org/W3196889659","https://openalex.org/W3198442913","https://openalex.org/W4210463634","https://openalex.org/W4224917454","https://openalex.org/W4224919446","https://openalex.org/W4225295099","https://openalex.org/W4225329198","https://openalex.org/W4283745191","https://openalex.org/W4293569541","https://openalex.org/W4296069150","https://openalex.org/W6638749077","https://openalex.org/W6713134421","https://openalex.org/W6743726175","https://openalex.org/W6751104502","https://openalex.org/W6752630080","https://openalex.org/W6760633627"],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W3198458223","https://openalex.org/W4288267738","https://openalex.org/W3126642501"],"abstract_inverted_index":{"Multilingual":[0],"end-to-end":[1],"automatic":[2],"speech":[3,54],"recognition":[4],"models":[5,23,39],"are":[6],"attractive":[7],"due":[8],"to":[9,29,75,115,127,135,139],"its":[10],"simplicity":[11],"in":[12,41],"training":[13,20],"and":[14,71,78,87,89,95,152],"deployment.":[15],"Recent":[16],"work":[17,34],"on":[18,37,108,149],"large-scale":[19],"of":[21,123],"such":[22],"has":[24],"shown":[25],"promising":[26],"results":[27],"compared":[28,114],"monolingual":[30],"models.":[31],"However,":[32],"the":[33,62,72,83,92,96,105,116,121,124,130],"often":[35],"focuses":[36],"multilingual":[38,53,76],"themselves":[40],"a":[42],"single-pass":[43,117],"setup.":[44],"In":[45],"this":[46],"work,":[47],"we":[48],"investigate":[49,81],"second-pass":[50],"deliberation":[51,58,84,93,103,125,145],"for":[52,141],"recognition.":[55],"Our":[56,144],"proposed":[57],"is":[59,147],"multilingual,":[60],"i.e.,":[61],"text":[63,67,77,85],"encoder":[64,86],"encodes":[65],"hypothesis":[66],"from":[68],"multiple":[69],"languages,":[70],"decoder":[73,94],"attends":[74],"audio.":[79],"We":[80,100],"scaling":[82,91],"decoder,":[88],"compare":[90],"first-pass":[97],"cascaded":[98],"encoder.":[99],"show":[101],"that":[102],"improves":[104],"average":[106,131],"WER":[107,132],"9":[109],"languages":[110],"by":[111],"4%":[112],"relative":[113],"model.":[118],"By":[119],"increasing":[120],"size":[122],"up":[126,138],"1B":[128],"parameters,":[129],"improvement":[133],"increases":[134],"9%,":[136],"with":[137],"14%":[140],"certain":[142],"languages.":[143],"rescorer":[146],"based":[148],"transformer":[150],"layers":[151],"can":[153],"be":[154],"parallelized":[155],"during":[156],"rescoring.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}