{"id":"https://openalex.org/W3008434450","doi":"https://doi.org/10.1109/asru46091.2019.9003870","title":"Leveraging Language ID in Multilingual End-to-End Speech Recognition","display_name":"Leveraging Language ID in Multilingual End-to-End Speech Recognition","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008434450","doi":"https://doi.org/10.1109/asru46091.2019.9003870","mag":"3008434450"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003870","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5064711844","display_name":"Austin Waters","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":"Austin Waters","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016601028","display_name":"Neeraj Gaur","orcid":"https://orcid.org/0000-0002-5926-9966"},"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":"Neeraj Gaur","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037705635","display_name":"Parisa Haghani","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":"Parisa Haghani","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103874391","display_name":"Pedro J. Moreno","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":"Pedro Moreno","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008909213","display_name":"Zhongdi Qu","orcid":"https://orcid.org/0009-0002-7789-712X"},"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":"Zhongdi Qu","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., 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":null,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"928","last_page":"935"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.8741079568862915},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7062719464302063},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.615809440612793},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6113683581352234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5450849533081055},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.530987560749054},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5298996567726135},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.46581414341926575},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23053571581840515}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8741079568862915},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7062719464302063},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.615809440612793},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6113683581352234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5450849533081055},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.530987560749054},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5298996567726135},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.46581414341926575},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23053571581840515},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003870","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W162588823","https://openalex.org/W1489125746","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W1982774639","https://openalex.org/W2108582047","https://openalex.org/W2108978495","https://openalex.org/W2127141656","https://openalex.org/W2178654303","https://openalex.org/W2291975472","https://openalex.org/W2327501763","https://openalex.org/W2402144811","https://openalex.org/W2605141709","https://openalex.org/W2606722458","https://openalex.org/W2617258110","https://openalex.org/W2633884958","https://openalex.org/W2746192915","https://openalex.org/W2767005120","https://openalex.org/W2767906378","https://openalex.org/W2772270478","https://openalex.org/W2913244614","https://openalex.org/W2953384591","https://openalex.org/W2962704885","https://openalex.org/W2962760690","https://openalex.org/W2962893195","https://openalex.org/W2963292011","https://openalex.org/W2963414781","https://openalex.org/W2963729263","https://openalex.org/W2963920996","https://openalex.org/W2964002616","https://openalex.org/W2964121744","https://openalex.org/W2964309797","https://openalex.org/W6676404333","https://openalex.org/W6713134421","https://openalex.org/W6735706088"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W4249048193","https://openalex.org/W2938107654","https://openalex.org/W2151749779","https://openalex.org/W3008587939","https://openalex.org/W3000360420","https://openalex.org/W1931440630","https://openalex.org/W2916997151","https://openalex.org/W2949174760"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,18,41,93,127],"end-to-end":[3],"speech":[4,17],"recognition":[5,134],"have":[6],"made":[7],"it":[8],"possible":[9],"to":[10,60,108],"build":[11],"multilingual":[12,133],"models,":[13],"capable":[14],"of":[15,32,38,51,77,120,131,140,148,152,155,161],"recognizing":[16],"multiple":[19],"languages.":[20,39],"Multilingual":[21],"models":[22,45],"can":[23],"outperform":[24],"their":[25],"monolingual":[26],"counterparts,":[27],"depending":[28],"on":[29,47,145],"the":[30,36,52,70,78,90,106,110,138,158],"amount":[31],"training":[33,128],"data":[34],"and":[35,99,129,157,165],"relatedness":[37],"However,":[40],"some":[42],"cases,":[43],"these":[44],"rely":[46],"having":[48],"perfect":[49],"knowledge":[50],"language":[53,66,91,111],"being":[54],"spoken;":[55],"that":[56,68,104],"is,":[57],"they":[58],"expect":[59],"be":[61],"provided":[62],"with":[63],"an":[64],"external":[65],"ID":[67,92],"augments":[69],"input":[71],"features":[72],"or":[73],"modulates":[74],"internal":[75],"layers":[76],"network.":[79],"In":[80],"this":[81,121],"paper,":[82],"we":[83],"introduce":[84],"a":[85,94,100,132],"novel":[86,101],"technique":[87],"for":[88],"inferring":[89],"streaming":[95,122],"fashion":[96],"using":[97],"RNN-T,":[98],"loss":[102],"function":[103],"pressures":[105],"model":[107,124],"identify":[109],"after":[112],"as":[113,116],"few":[114],"frames":[115],"possible.":[117],"The":[118],"output":[119],"language-ID":[123],"is":[125],"used":[126],"inference":[130],"model.":[135],"We":[136],"show":[137],"effectiveness":[139],"our":[141],"approach":[142],"through":[143],"experiments":[144],"two":[146],"sets":[147],"languages,":[149,163],"one":[150],"consisting":[151,160],"different":[153],"dialects":[154],"Arabic,":[156],"other":[159],"Nordic":[162],"Finnish":[164],"Dutch.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}