{"id":"https://openalex.org/W2970611152","doi":"https://doi.org/10.21437/interspeech.2019-1341","title":"Two-Pass End-to-End Speech Recognition","display_name":"Two-Pass End-to-End Speech Recognition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2970611152","doi":"https://doi.org/10.21437/interspeech.2019-1341","mag":"2970611152"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1341","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1341","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1908.10992","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112901893","display_name":"Ruoming Pang","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":"Ruoming Pang","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050133412","display_name":"David Rybach","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":"David Rybach","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319167","display_name":"Yanzhang He","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":"Yanzhang He","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","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 (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318291","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-8278-1765"},"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":"Wei Li","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051478984","display_name":"Mirk\u00f3 Visontai","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":"Mirk\u00f3 Visontai","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026297587","display_name":"Qiao Liang","orcid":"https://orcid.org/0000-0003-4464-4644"},"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":"Qiao Liang","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032931723","display_name":"Trevor Strohman","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":"Trevor Strohman","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","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 (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048236120","display_name":"Ian McGraw","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":"Ian McGraw","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027763497","display_name":"Chung\u2010Cheng Chiu","orcid":"https://orcid.org/0000-0001-9729-4778"},"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":"Chung-Cheng Chiu","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5070513394"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.99703069,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89160264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2773","last_page":"2777"},"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/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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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":0.8559883832931519},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7582799196243286},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7029537558555603},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6896870136260986},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6130607724189758},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6098248362541199},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49817490577697754},{"id":"https://openalex.org/keywords/spell","display_name":"Spell","score":0.4764278829097748},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3734881281852722},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.32524046301841736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2968336045742035},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13409188389778137}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8559883832931519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7582799196243286},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7029537558555603},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6896870136260986},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6130607724189758},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6098248362541199},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49817490577697754},{"id":"https://openalex.org/C2780957641","wikidata":"https://www.wikidata.org/wiki/Q1999796","display_name":"Spell","level":2,"score":0.4764278829097748},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3734881281852722},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.32524046301841736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2968336045742035},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13409188389778137},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-1341","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1341","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"},{"id":"pmh:oai:arXiv.org:1908.10992","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.10992","pdf_url":"https://arxiv.org/pdf/1908.10992","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2970611152","is_oa":true,"landing_page_url":"https://www.arxiv.org/pdf/1908.10992","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1908.10992","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1908.10992","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1908.10992","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.10992","pdf_url":"https://arxiv.org/pdf/1908.10992","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970611152.pdf","grobid_xml":"https://content.openalex.org/works/W2970611152.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W1985258458","https://openalex.org/W2022951240","https://openalex.org/W2089666999","https://openalex.org/W2121879602","https://openalex.org/W2137095888","https://openalex.org/W2164579587","https://openalex.org/W2271840356","https://openalex.org/W2293829681","https://openalex.org/W2345190899","https://openalex.org/W2403440562","https://openalex.org/W2507771204","https://openalex.org/W2515439472","https://openalex.org/W2526425061","https://openalex.org/W2577366047","https://openalex.org/W2617258110","https://openalex.org/W2626778328","https://openalex.org/W2749514303","https://openalex.org/W2886319145","https://openalex.org/W2928941594","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2963240019","https://openalex.org/W2963414781","https://openalex.org/W2963660642","https://openalex.org/W2963747784"],"related_works":["https://openalex.org/W2936774411","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W854541894","https://openalex.org/W2963403868","https://openalex.org/W2327501763","https://openalex.org/W2901837390","https://openalex.org/W3095994005","https://openalex.org/W3108184206","https://openalex.org/W2795935804","https://openalex.org/W2775304348","https://openalex.org/W3018441253","https://openalex.org/W2984841584","https://openalex.org/W3097054834","https://openalex.org/W2981532039","https://openalex.org/W3196784225","https://openalex.org/W3012641541","https://openalex.org/W2947278894","https://openalex.org/W3148986242","https://openalex.org/W3096735052"],"abstract_inverted_index":{"The":[0],"requirements":[1],"for":[2,23,60],"many":[3,24],"applications":[4],"of":[5,119,127],"state-of-the-art":[6,84],"speech":[7,62],"recognition":[8],"systems":[9],"include":[10],"not":[11],"only":[12],"low":[13,20],"word":[14],"error":[15],"rate":[16],"(WER)":[17],"but":[18],"also":[19],"latency.":[21],"Specifically,":[22],"use-cases,":[25],"the":[26,91,117],"system":[27,130],"must":[28],"be":[29,56],"able":[30],"to":[31,55,71,107,115,125,158],"decode":[32],"utterances":[33],"in":[34,87,155],"a":[35,43,57,82,94,128,133,137,151,165],"streaming":[36,44,122],"fashion":[37],"and":[38,67,99,161],"faster":[39],"than":[40],"real-time.":[41],"Recently,":[42],"recurrent":[45],"neural":[46],"network":[47,135],"transducer":[48],"(RNN-T)":[49],"end-to-end":[50],"(E2E)":[51],"model":[52,78,86,102,123,149],"has":[53,103],"shown":[54,104],"good":[58],"candidate":[59],"on-device":[61,73],"recognition,":[63],"with":[64],"improved":[65],"WER":[66,156],"latency":[68,144,163],"metrics":[69],"compared":[70,157],"conventional":[72,85,109,129],"models":[74,110],"[1].":[75],"However,":[76],"this":[77],"still":[79,141],"lags":[80],"behind":[81],"large":[83,108],"quality":[88,106,118],"[2].":[89],"On":[90],"other":[92],"hand,":[93],"non-streaming":[95],"E2E":[96,121],"Listen,":[97],"Attend":[98],"Spell":[100],"(LAS)":[101],"comparable":[105],"[3].":[111],"This":[112],"work":[113],"aims":[114],"bring":[116],"an":[120],"closer":[124],"that":[126],"by":[131,143,164],"incorporating":[132],"LAS":[134],"as":[136],"second-pass":[138],"component,":[139],"while":[140],"abiding":[142],"constraints.":[145],"Our":[146],"proposed":[147],"two-pass":[148],"achieves":[150],"17%-22%":[152],"relative":[153],"reduction":[154],"RNN-T":[159],"alone":[160],"increases":[162],"small":[166],"fraction":[167],"over":[168],"RNN-T.":[169]},"counts_by_year":[{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}