{"id":"https://openalex.org/W3095503786","doi":"https://doi.org/10.1109/icassp39728.2021.9414607","title":"Cascaded Encoders for Unifying Streaming and Non-Streaming ASR","display_name":"Cascaded Encoders for Unifying Streaming and Non-Streaming ASR","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3095503786","doi":"https://doi.org/10.1109/icassp39728.2021.9414607","mag":"3095503786"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/2010.14606","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 LLC, USA","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","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 LLC, USA","[Google, LLC, USA]"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google, LLC, USA]","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 LLC, USA","[Google, LLC, USA]"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google, LLC, USA]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001205723","display_name":"Jiahui Yu","orcid":"https://orcid.org/0000-0003-1314-2481"},"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":"Jiahui Yu","raw_affiliation_strings":["Google LLC, USA","[Google, LLC, USA]"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google, LLC, 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 LLC, USA","[Google, LLC, USA]"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google, LLC, 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 LLC, USA","[Google, LLC, USA]"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google, LLC, USA]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040131037","display_name":"Ehsan Variani","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":"Ehsan Variani","raw_affiliation_strings":["Google LLC, USA","[Google, LLC, USA]"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google, LLC, 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 LLC, USA","[Google, LLC, USA]"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google, LLC, USA]","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5000078382"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.5644143,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70910535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9986000061035156,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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/encoder","display_name":"Encoder","score":0.9177056550979614},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8252216577529907},{"id":"https://openalex.org/keywords/streaming-current","display_name":"Streaming current","score":0.6839785575866699},{"id":"https://openalex.org/keywords/streaming-algorithm","display_name":"Streaming algorithm","score":0.6028025150299072},{"id":"https://openalex.org/keywords/streaming-data","display_name":"Streaming data","score":0.5182128548622131},{"id":"https://openalex.org/keywords/video-streaming","display_name":"Video streaming","score":0.5003135204315186},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.4824550747871399},{"id":"https://openalex.org/keywords/acoustic-streaming","display_name":"Acoustic streaming","score":0.4754764139652252},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.383819043636322},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.14933642745018005},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.06292450428009033}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.9177056550979614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252216577529907},{"id":"https://openalex.org/C30311675","wikidata":"https://www.wikidata.org/wiki/Q7622689","display_name":"Streaming current","level":3,"score":0.6839785575866699},{"id":"https://openalex.org/C187166803","wikidata":"https://www.wikidata.org/wiki/Q2835831","display_name":"Streaming algorithm","level":3,"score":0.6028025150299072},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.5182128548622131},{"id":"https://openalex.org/C2986160907","wikidata":"https://www.wikidata.org/wiki/Q220499","display_name":"Video streaming","level":2,"score":0.5003135204315186},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.4824550747871399},{"id":"https://openalex.org/C2779019082","wikidata":"https://www.wikidata.org/wiki/Q4674713","display_name":"Acoustic streaming","level":3,"score":0.4754764139652252},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.383819043636322},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.14933642745018005},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.06292450428009033},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C81288441","wikidata":"https://www.wikidata.org/wiki/Q20736125","display_name":"Ultrasonic sensor","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C147789679","wikidata":"https://www.wikidata.org/wiki/Q11372","display_name":"Physical chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C27703432","wikidata":"https://www.wikidata.org/wiki/Q2778467","display_name":"Electrokinetic phenomena","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.14606","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.14606","pdf_url":"https://arxiv.org/pdf/2010.14606","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":null},{"id":"mag:3095503786","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.14606.pdf","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.2010.14606","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.14606","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"},{"id":"doi:10.17023/5q74-1r52","is_oa":true,"landing_page_url":"https://doi.org/10.17023/5q74-1r52","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:2010.14606","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.14606","pdf_url":"https://arxiv.org/pdf/2010.14606","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":null},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095503786.pdf"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W2121879602","https://openalex.org/W2127141656","https://openalex.org/W2138889249","https://openalex.org/W2327501763","https://openalex.org/W2329068866","https://openalex.org/W2402144811","https://openalex.org/W2507771204","https://openalex.org/W2526425061","https://openalex.org/W2606722458","https://openalex.org/W2617258110","https://openalex.org/W2752047430","https://openalex.org/W2773723600","https://openalex.org/W2928941594","https://openalex.org/W2936774411","https://openalex.org/W2953212265","https://openalex.org/W2962893195","https://openalex.org/W2963122170","https://openalex.org/W2963403868","https://openalex.org/W2963928591","https://openalex.org/W2964084166","https://openalex.org/W2973122799","https://openalex.org/W2982413405","https://openalex.org/W2984841584","https://openalex.org/W3008181812","https://openalex.org/W3008898571","https://openalex.org/W3011339933","https://openalex.org/W3015194534","https://openalex.org/W3015927303","https://openalex.org/W3016010032","https://openalex.org/W3021469861","https://openalex.org/W3025165719","https://openalex.org/W3032859754","https://openalex.org/W3092122846","https://openalex.org/W3093346109","https://openalex.org/W3095173472","https://openalex.org/W3095311338","https://openalex.org/W3097777922","https://openalex.org/W3105169251","https://openalex.org/W3163907627","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6713134421","https://openalex.org/W6739901393","https://openalex.org/W6743726175","https://openalex.org/W6746924902","https://openalex.org/W6760633627","https://openalex.org/W6769806307","https://openalex.org/W6775998690","https://openalex.org/W6779752190","https://openalex.org/W6784192591","https://openalex.org/W6784400248","https://openalex.org/W6784800133"],"related_works":["https://openalex.org/W3163203022","https://openalex.org/W3016010032","https://openalex.org/W2982413405","https://openalex.org/W1828163288","https://openalex.org/W1966358021","https://openalex.org/W2734968834","https://openalex.org/W2128710359","https://openalex.org/W2536884064","https://openalex.org/W2018892528","https://openalex.org/W2062751292","https://openalex.org/W2159325139","https://openalex.org/W2736660110","https://openalex.org/W2589802337","https://openalex.org/W1500196796","https://openalex.org/W232434037","https://openalex.org/W2118014251","https://openalex.org/W3093392128","https://openalex.org/W1998378504","https://openalex.org/W2167625879","https://openalex.org/W2132132033"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"automatic":[2],"speech":[3],"recognition":[4],"(ASR)":[5],"models,":[6,141],"by":[7,62],"now,":[8],"have":[9],"shown":[10],"competitive":[11],"performance":[12],"on":[13,71,143],"several":[14],"benchmarks.":[15],"These":[16],"models":[17],"are":[18,59],"structured":[19],"to":[20,83],"either":[21,85],"operate":[22,42],"in":[23,43,114,126],"streaming":[24,53,64,76,91,110,115],"or":[25,92],"non-streaming":[26,55,67,94,127],"mode.":[27,128],"This":[28],"work":[29],"presents":[30],"cascaded":[31],"encoders":[32],"for":[33],"building":[34],"a":[35,108],"single":[36,79],"E2E":[37,139],"ASR":[38],"model":[39,50,100,111],"that":[40,98,133],"can":[41],"both":[44],"these":[45],"modes":[46],"simultaneously.":[47],"The":[48],"proposed":[49,135],"consists":[51],"of":[52,74,89],"and":[54,117],"encoders.":[56],"Input":[57],"features":[58],"first":[60],"processed":[61],"the":[63,66,72,75,87,90,93,134],"encoder;":[65],"encoder":[68],"operates":[69],"exclusively":[70],"output":[73,88],"encoder.":[77,95],"A":[78],"decoder":[80],"then":[81],"learns":[82],"decode":[84],"using":[86],"Results":[96],"show":[97,132],"this":[99],"achieves":[101],"similar":[102],"word":[103],"error":[104],"rates":[105],"(WER)":[106],"as":[107],"standalone":[109],"when":[112,124],"operating":[113,125],"mode,":[116],"obtains":[118],"10%":[119],"--":[120],"27%":[121],"relative":[122],"improvement":[123],"Our":[129],"results":[130],"also":[131],"approach":[136],"outperforms":[137],"existing":[138],"two-pass":[140],"especially":[142],"long-form":[144],"speech.":[145]},"counts_by_year":[{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}