{"id":"https://openalex.org/W2971840980","doi":"https://doi.org/10.21437/interspeech.2019-2858","title":"Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model","display_name":"Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2971840980","doi":"https://doi.org/10.21437/interspeech.2019-2858","mag":"2971840980"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2858","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5023098355","display_name":"Anjuli Kannan","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":"Anjuli Kannan","raw_affiliation_strings":["Google, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036200604","display_name":"Arindrima Datta","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":"Arindrima Datta","raw_affiliation_strings":["Google, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","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, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058585526","display_name":"Eugene Weinstein","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":"Eugene Weinstein","raw_affiliation_strings":["Google, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010253402","display_name":"Yonghui Wu","orcid":"https://orcid.org/0000-0002-6780-6135"},"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":"Yonghui Wu","raw_affiliation_strings":["Google, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024316712","display_name":"Ankur Bapna","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":"Ankur Bapna","raw_affiliation_strings":["Google, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100715424","display_name":"Zhifeng Chen","orcid":"https://orcid.org/0000-0001-8631-2424"},"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":"Zhifeng Chen","raw_affiliation_strings":["Google, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006601657","display_name":"Seungji Lee","orcid":"https://orcid.org/0000-0002-7279-9822"},"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":"Seungji Lee","raw_affiliation_strings":["Google, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","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":158,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2130","last_page":"2134"},"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":0.9988999962806702,"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":0.9983999729156494,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.9056583046913147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7303922176361084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5495043992996216},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5066824555397034},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.4710127115249634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3544018864631653},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15451061725616455},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07947444915771484}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.9056583046913147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7303922176361084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5495043992996216},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5066824555397034},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.4710127115249634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3544018864631653},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15451061725616455},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07947444915771484},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-2858","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W1975550806","https://openalex.org/W1978660892","https://openalex.org/W1994606281","https://openalex.org/W2001458616","https://openalex.org/W2025401819","https://openalex.org/W2094147890","https://openalex.org/W2114016253","https://openalex.org/W2127982613","https://openalex.org/W2134054733","https://openalex.org/W2276408190","https://openalex.org/W2291975472","https://openalex.org/W2293009711","https://openalex.org/W2533125211","https://openalex.org/W2633884958","https://openalex.org/W2716988359","https://openalex.org/W2769437540","https://openalex.org/W2786835190","https://openalex.org/W2894835365","https://openalex.org/W2913244614","https://openalex.org/W2914699162","https://openalex.org/W2928941594","https://openalex.org/W2953212265","https://openalex.org/W2962361184","https://openalex.org/W2962760690","https://openalex.org/W2962893195","https://openalex.org/W2963211188","https://openalex.org/W2963414781","https://openalex.org/W2964002616","https://openalex.org/W2964303773","https://openalex.org/W2970925270","https://openalex.org/W2972347614"],"related_works":["https://openalex.org/W4299590256","https://openalex.org/W2368779261","https://openalex.org/W2778699561","https://openalex.org/W2951281592","https://openalex.org/W4284893874","https://openalex.org/W3163634122","https://openalex.org/W2971982237","https://openalex.org/W2919182614","https://openalex.org/W2938947737","https://openalex.org/W1547975896"],"abstract_inverted_index":{"Multilingual":[0],"end-to-end":[1],"(E2E)":[2],"models":[3,117],"have":[4,20,27],"shown":[5,21],"great":[6],"promise":[7],"in":[8,51,68],"expansion":[9],"of":[10,16,62,80,87,119],"automatic":[11],"speech":[12],"recognition":[13],"(ASR)":[14],"coverage":[15],"the":[17,66,99],"world's":[18],"languages.They":[19],"improvement":[22],"over":[23],"monolingual":[24,115,123],"systems,":[25],"and":[26,30,37,82,93,122],"simplified":[28],"training":[29,69,94],"serving":[31],"by":[32],"eliminating":[33],"language-specific":[34,95],"acoustic,":[35],"pronunciation,":[36],"language":[38,91],"models.This":[39],"work":[40],"presents":[41],"an":[42],"E2E":[43,103,116],"multilingual":[44,104],"system":[45],"which":[46],"is":[47],"equipped":[48],"to":[49],"operate":[50],"low-latency":[52],"interactive":[53],"applications,":[54],"as":[55,57],"well":[56],"handle":[58],"a":[59,78,85,90,107],"key":[60],"challenge":[61],"real":[63],"world":[64],"data:":[65],"imbalance":[67],"data":[70],"across":[71],"languages.Using":[72],"nine":[73,120,127],"Indic":[74],"languages,":[75],"we":[76],"compare":[77],"variety":[79],"techniques,":[81],"find":[83],"that":[84],"combination":[86],"conditioning":[88],"on":[89],"vector":[92],"adapter":[96],"layers":[97],"produces":[98],"best":[100],"model.The":[101],"resulting":[102],"model":[105],"achieves":[106],"lower":[108],"word":[109],"error":[110],"rate":[111],"(WER)":[112],"than":[113],"both":[114],"(eight":[118],"languages)":[121],"conventional":[124],"systems":[125],"(all":[126],"languages).":[128]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":29},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}