{"id":"https://openalex.org/W2981532039","doi":"https://doi.org/10.1109/asru46091.2019.9003913","title":"Recognizing Long-Form Speech Using Streaming End-to-End Models","display_name":"Recognizing Long-Form Speech Using Streaming End-to-End Models","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2981532039","doi":"https://doi.org/10.1109/asru46091.2019.9003913","mag":"2981532039"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003913","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.11455","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Arun Narayanan","raw_affiliation_strings":["Google, USA","Google  USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google  USA","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, USA","Google  USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google  USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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, USA","Google  USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google  USA","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, USA","Google  USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google  USA","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, USA","Google  USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google  USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","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, USA","Google  USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google  USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5000078382"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.46085324,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7171142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"920","last_page":"927"},"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":0.9991999864578247,"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":0.9986000061035156,"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":0.7541109323501587},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6690492033958435},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6652593612670898},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6267008781433105},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6166398525238037},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6142618060112},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.6118239760398865},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5962618589401245},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5527580380439758},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.49964141845703125},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4411679208278656},{"id":"https://openalex.org/keywords/approximation-error","display_name":"Approximation error","score":0.427153080701828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3910177946090698},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11457589268684387},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0981774628162384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541109323501587},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6690492033958435},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6652593612670898},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6267008781433105},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6166398525238037},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6142618060112},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.6118239760398865},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5962618589401245},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5527580380439758},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.49964141845703125},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4411679208278656},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.427153080701828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3910177946090698},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11457589268684387},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0981774628162384},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru46091.2019.9003913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003913","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"},{"id":"pmh:oai:arXiv.org:1910.11455","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11455","pdf_url":"https://arxiv.org/pdf/1910.11455","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:2981532039","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.11455v1","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.1910.11455","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.11455","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:1910.11455","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11455","pdf_url":"https://arxiv.org/pdf/1910.11455","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":[{"score":0.6800000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2981532039.pdf","grobid_xml":"https://content.openalex.org/works/W2981532039.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W1922655562","https://openalex.org/W1971129545","https://openalex.org/W2033256038","https://openalex.org/W2064675550","https://openalex.org/W2069143585","https://openalex.org/W2121879602","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2137095888","https://openalex.org/W2137644731","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2402144811","https://openalex.org/W2491408735","https://openalex.org/W2507771204","https://openalex.org/W2510616059","https://openalex.org/W2545177271","https://openalex.org/W2597757402","https://openalex.org/W2606722458","https://openalex.org/W2617258110","https://openalex.org/W2627092829","https://openalex.org/W2739427748","https://openalex.org/W2750499125","https://openalex.org/W2786459654","https://openalex.org/W2799800213","https://openalex.org/W2911109671","https://openalex.org/W2928941594","https://openalex.org/W2936774411","https://openalex.org/W2953212265","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2963122170","https://openalex.org/W2963414781","https://openalex.org/W2963827914","https://openalex.org/W2964138484","https://openalex.org/W2964272710","https://openalex.org/W2973122799","https://openalex.org/W2984841584","https://openalex.org/W3008898571","https://openalex.org/W6623517193","https://openalex.org/W6679436768","https://openalex.org/W6687566353","https://openalex.org/W6688428952","https://openalex.org/W6713134421","https://openalex.org/W6741807409","https://openalex.org/W6743440867","https://openalex.org/W6747158283","https://openalex.org/W6747398299","https://openalex.org/W6748211734"],"related_works":["https://openalex.org/W3008181812","https://openalex.org/W2900312178","https://openalex.org/W3198413388","https://openalex.org/W3108266107","https://openalex.org/W2901837390","https://openalex.org/W1543325588","https://openalex.org/W2775304348","https://openalex.org/W3012645992","https://openalex.org/W2798949062","https://openalex.org/W1495019370","https://openalex.org/W2992448548","https://openalex.org/W2952181946","https://openalex.org/W2765507192","https://openalex.org/W3108184206","https://openalex.org/W2953022181","https://openalex.org/W3008284571","https://openalex.org/W2787133659","https://openalex.org/W1494243555","https://openalex.org/W3125708547","https://openalex.org/W2520176975"],"abstract_inverted_index":{"All-neural":[0],"end-to-end":[1],"(E2E)":[2],"automatic":[3],"speech":[4],"recognition":[5],"(ASR)":[6],"systems":[7],"that":[8,48],"use":[9],"a":[10,87,122],"single":[11],"neural":[12],"network":[13],"to":[14,17,23,40,42,55,57,65,77],"transduce":[15],"audio":[16,80],"word":[18,96],"sequences":[19],"have":[20],"been":[21],"shown":[22],"achieve":[24],"state-of-the-art":[25],"results":[26],"on":[27,51,69,139],"several":[28],"tasks.":[29],"In":[30],"this":[31],"work,":[32],"we":[33,46],"examine":[34],"the":[35,113],"ability":[36],"of":[37,141],"E2E":[38],"models":[39,49],"generalize":[41,56],"unseen":[43],"domains,":[44],"where":[45],"find":[47],"trained":[50],"short":[52,84],"utterances":[53],"fail":[54],"long-form":[58,79,89,105,124,137],"speech.":[59],"We":[60],"propose":[61],"two":[62],"complementary":[63],"solutions":[64],"address":[66],"this:":[67],"training":[68,82,106,138],"diverse":[70],"acoustic":[71],"data,":[72],"and":[73],"LSTM":[74],"state":[75],"manipulation":[76],"simulate":[78],"when":[81],"using":[83],"utterances.":[85],"On":[86,121],"synthesized":[88],"test":[90,126],"set,":[91,127],"adding":[92,128],"data":[93,118,129,142],"diversity":[94,119,130,143],"improves":[95,107,131,144],"error":[97],"rate":[98],"(WER)":[99],"by":[100,109,133,146],"90%":[101],"relative,":[102,111],"while":[103],"simulating":[104],"it":[108],"67%":[110],"though":[112],"combination":[114],"doesn't":[115],"improve":[116],"over":[117],"alone.":[120],"real":[123],"call-center":[125],"WER":[132],"40%":[134],"relative.":[135,150],"Simulating":[136],"top":[140],"performance":[145],"an":[147],"additional":[148],"27%":[149]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}