{"id":"https://openalex.org/W3098649167","doi":"https://doi.org/10.1109/slt48900.2021.9383504","title":"Streaming Attention-Based Models with Augmented Memory for End-To-End Speech Recognition","display_name":"Streaming Attention-Based Models with Augmented Memory for End-To-End Speech Recognition","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3098649167","doi":"https://doi.org/10.1109/slt48900.2021.9383504","mag":"3098649167"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.07120","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087421101","display_name":"Ching-Feng Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ching-Feng Yeh","raw_affiliation_strings":["Facebook AI, USA","Facebook AI,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339989","display_name":"Yongqiang Wang","orcid":"https://orcid.org/0000-0002-8600-0276"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongqiang Wang","raw_affiliation_strings":["Facebook AI, USA","Facebook AI,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103247973","display_name":"Yangyang Shi","orcid":"https://orcid.org/0000-0001-5297-4155"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yangyang Shi","raw_affiliation_strings":["Facebook AI, USA","Facebook AI,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101579713","display_name":"Chunyang Wu","orcid":"https://orcid.org/0000-0002-0269-3555"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunyang Wu","raw_affiliation_strings":["Facebook AI, USA","Facebook AI,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101984914","display_name":"Frank Zhang","orcid":"https://orcid.org/0000-0001-9946-6502"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank Zhang","raw_affiliation_strings":["Facebook AI, USA","Facebook AI,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051075420","display_name":"Julian Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian Chan","raw_affiliation_strings":["Facebook AI, USA","Facebook AI,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Seltzer","raw_affiliation_strings":["Facebook AI, USA","Facebook AI,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":0.1465,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32360404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"8","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.7892650365829468},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6442205309867859},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5719643831253052},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5609712600708008},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.48824217915534973},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4508693516254425},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.4111277163028717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29472121596336365},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08174359798431396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7892650365829468},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6442205309867859},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5719643831253052},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5609712600708008},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.48824217915534973},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4508693516254425},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.4111277163028717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29472121596336365},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08174359798431396},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/slt48900.2021.9383504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.07120","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.07120","pdf_url":"https://arxiv.org/pdf/2011.07120","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2011.07120","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.07120","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},{"id":"doi:10.17023/vaxb-wt08","is_oa":true,"landing_page_url":"https://doi.org/10.17023/vaxb-wt08","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"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":"Audiovisual"},{"id":"mag:3098649167","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.07120","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.07120","pdf_url":"https://arxiv.org/pdf/2011.07120","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3098649167.pdf","grobid_xml":"https://content.openalex.org/works/W3098649167.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2064675550","https://openalex.org/W2327501763","https://openalex.org/W2802023636","https://openalex.org/W2885185669","https://openalex.org/W2913718171","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2941814890","https://openalex.org/W2962760690","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963250244","https://openalex.org/W2963403868","https://openalex.org/W2964110616","https://openalex.org/W2981857663","https://openalex.org/W2982413405","https://openalex.org/W3007073761","https://openalex.org/W3015537910","https://openalex.org/W3016010032","https://openalex.org/W3021469861","https://openalex.org/W3025165719","https://openalex.org/W3027588817","https://openalex.org/W3095173472","https://openalex.org/W3096888553","https://openalex.org/W3097075707","https://openalex.org/W3097558625","https://openalex.org/W3097777922","https://openalex.org/W6638749077","https://openalex.org/W6640059789","https://openalex.org/W6739901393","https://openalex.org/W6761563299","https://openalex.org/W6769557084","https://openalex.org/W6769806307","https://openalex.org/W6769971416"],"related_works":["https://openalex.org/W3093706254","https://openalex.org/W3166295848","https://openalex.org/W3199681947","https://openalex.org/W3033604713","https://openalex.org/W3092122846","https://openalex.org/W3083872384","https://openalex.org/W3082786707","https://openalex.org/W3185456526","https://openalex.org/W3091202141","https://openalex.org/W3046754651","https://openalex.org/W3034413489","https://openalex.org/W3188619050","https://openalex.org/W2015007741","https://openalex.org/W2981858655","https://openalex.org/W3203089423","https://openalex.org/W3138127198","https://openalex.org/W2026835084","https://openalex.org/W3110243964","https://openalex.org/W3163652387","https://openalex.org/W3090576180"],"abstract_inverted_index":{"Attention-based":[0],"models":[1,29,100],"have":[2],"been":[3],"gaining":[4],"popularity":[5],"recently":[6],"for":[7,54],"their":[8],"strong":[9],"performance":[10],"demonstrated":[11],"in":[12],"fields":[13],"such":[14],"as":[15],"machine":[16],"translation":[17],"[1]":[18],"and":[19,39,73,105,135],"automatic":[20],"speech":[21,75],"recognition":[22,76],"[2].":[23,93],"One":[24],"major":[25],"challenge":[26],"of":[27,33,80],"attention-based":[28,88,113],"is":[30,60],"the":[31,36,40,46,58,81,98,102,107,111,121,143],"need":[32],"access":[34],"to":[35,63,139],"full":[37],"sequence":[38,47],"quadratically":[41],"growing":[42],"computational":[43],"cost":[44],"concerning":[45],"length.":[48],"These":[49],"characteristics":[50],"pose":[51],"challenges,":[52],"especially":[53],"low-latency":[55],"scenarios,":[56],"where":[57],"system":[59,77,96,127],"often":[61],"required":[62],"be":[64],"streaming.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"build":[70],"a":[71],"compact":[72],"streaming":[74,103,112,146],"on":[78,133,137],"top":[79],"end-to-end":[82,99],"neural":[83],"transducer":[84],"architecture":[85],"[3]":[86],"with":[87,91,101],"modules":[89],"augmented":[90,116],"convolution":[92],"The":[94],"proposed":[95,126],"equips":[97],"capability":[104],"reduces":[106],"large":[108],"footprint":[109],"from":[110],"model":[114],"using":[115],"memory":[117],"[4],":[118],"[5].":[119],"On":[120],"LibriSpeech":[122],"[6]":[123],"dataset,":[124],"our":[125,140],"achieves":[128],"word":[129],"error":[130],"rates":[131],"2.7%":[132],"test-clean":[134],"5.8%":[136],"test-other,":[138],"best":[141],"knowledge":[142],"lowest":[144],"among":[145],"approaches":[147],"reported":[148],"so":[149],"far.":[150]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}