{"id":"https://openalex.org/W3008898571","doi":"https://doi.org/10.1109/asru46091.2019.9003854","title":"A Comparison of End-to-End Models for Long-Form Speech Recognition","display_name":"A Comparison of End-to-End Models for Long-Form Speech Recognition","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008898571","doi":"https://doi.org/10.1109/asru46091.2019.9003854","mag":"3008898571"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003854","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/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 Inc, Grab Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Grab Technologies","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750907","display_name":"Wei Han","orcid":"https://orcid.org/0000-0002-4201-9645"},"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 Han","raw_affiliation_strings":["Google Inc, Grab Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Grab Technologies","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092336773","display_name":"Yu Zhang","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":"Yu Zhang","raw_affiliation_strings":["Google Inc, Grab Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Grab Technologies","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 Inc, Grab Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Grab Technologies","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040816983","display_name":"Sergey Kishchenko","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":"Sergey Kishchenko","raw_affiliation_strings":["Google Inc, Grab Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Grab Technologies","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113878965","display_name":"Patrick Nguyen","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":"Patrick Nguyen","raw_affiliation_strings":["Google Inc, Grab Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Grab Technologies","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"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":"Arun Narayanan","raw_affiliation_strings":["Google Inc, Grab Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Grab Technologies","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110698977","display_name":"Hank Liao","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":"Hank Liao","raw_affiliation_strings":["Google Inc, Grab Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Grab Technologies","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699726","display_name":"Shuyuan Zhang","orcid":"https://orcid.org/0000-0001-5218-2668"},"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":"Shuyuan Zhang","raw_affiliation_strings":["Google Inc, Grab Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Grab Technologies","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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, Grab Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Grab Technologies","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 Inc, Grab Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Grab Technologies","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, Grab Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Grab Technologies","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 Sainath","raw_affiliation_strings":["Google Inc, Grab Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Grab Technologies","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","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, Grab Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Grab Technologies","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":5.5765,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.96999843,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"889","last_page":"896"},"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/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"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/T12031","display_name":"Speech and dialogue systems","score":0.9959999918937683,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.9101917743682861},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7963738441467285},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7287362217903137},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6611278653144836},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6041576266288757},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.457580029964447},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43927937746047974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4084053337574005},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3313538432121277},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1435030698776245},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07329681515693665}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.9101917743682861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7963738441467285},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7287362217903137},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6611278653144836},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6041576266288757},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.457580029964447},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43927937746047974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4084053337574005},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3313538432121277},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1435030698776245},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07329681515693665},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003854","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1810943226","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W2033256038","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2530876040","https://openalex.org/W2545177271","https://openalex.org/W2605141709","https://openalex.org/W2750499125","https://openalex.org/W2767601419","https://openalex.org/W2786076697","https://openalex.org/W2889129739","https://openalex.org/W2901837390","https://openalex.org/W2911544293","https://openalex.org/W2928941594","https://openalex.org/W2952992734","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963122170","https://openalex.org/W2963827914","https://openalex.org/W2964272710","https://openalex.org/W4294619417","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6639156005","https://openalex.org/W6675365184","https://openalex.org/W6735706088","https://openalex.org/W6741807409","https://openalex.org/W6743440867","https://openalex.org/W6747158283"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W2578422401","https://openalex.org/W2160451571","https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W2495256954"],"abstract_inverted_index":{"End-to-end":[0],"automatic":[1],"speech":[2,169],"recognition":[3],"(ASR)":[4],"models,":[5],"including":[6],"both":[7,74],"attention-based":[8,113,124,158],"models":[9,82,95,160],"and":[10,76,102,137],"the":[11,78,105,132],"recurrent":[12],"neural":[13],"network":[14],"transducer":[15],"(RNN-T),":[16],"have":[17,30],"shown":[18],"superior":[19],"performance":[20,79],"compared":[21],"to":[22,64,123,134,165],"conventional":[23],"systems":[24,114,125],"[1],":[25],"[2].":[26],"However,":[27],"previous":[28],"studies":[29],"focused":[31],"primarily":[32],"on":[33,57,83,96,167],"short":[34],"utterances":[35,59,146],"that":[36,60,104,126,143,157],"typically":[37],"last":[38,61],"for":[39],"just":[40],"a":[41,47,97,139],"few":[42,48],"seconds":[43],"or,":[44],"at":[45],"most,":[46],"tens":[49],"of":[50,80,92],"seconds.":[51],"Whether":[52],"such":[53],"architectures":[54],"are":[55],"practical":[56],"long":[58,145],"from":[62],"minutes":[63],"hours":[65],"remains":[66],"an":[67,89],"open":[68],"question.":[69],"In":[70],"this":[71,116],"paper,":[72],"we":[73,155],"investigate":[75],"improve":[77,128],"end-to-end":[81,94,159],"long-form":[84,100,168],"transcription.":[85],"We":[86,118],"first":[87],"present":[88],"empirical":[90],"comparison":[91],"different":[93],"real":[98],"world":[99],"task":[101],"demonstrate":[103],"RNN-T":[106,166],"model":[107],"is":[108],"much":[109],"more":[110],"robust":[111],"than":[112],"in":[115],"regime.":[117],"next":[119],"explore":[120],"two":[121,153],"improvements":[122],"significantly":[127],"its":[129],"performance:":[130],"restricting":[131],"attention":[133],"be":[135,162],"monotonic,":[136],"applying":[138],"novel":[140],"decoding":[141],"algorithm":[142],"breaks":[144],"into":[147],"shorter":[148],"overlapping":[149],"segments.":[150],"Combining":[151],"these":[152],"improvements,":[154],"show":[156],"can":[161],"very":[163],"competitive":[164],"recognition.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}