{"id":"https://openalex.org/W3207629995","doi":"https://doi.org/10.1109/icassp43922.2022.9747706","title":"Streaming Transformer Transducer based Speech Recognition Using Non-Causal Convolution","display_name":"Streaming Transformer Transducer based Speech Recognition Using Non-Causal Convolution","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207629995","doi":"https://doi.org/10.1109/icassp43922.2022.9747706","mag":"3207629995"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747706","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5103247973","display_name":"Yangyang Shi","orcid":"https://orcid.org/0000-0001-5297-4155"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Yangyang Shi","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"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/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Chunyang Wu","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016340673","display_name":"Dilin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dilin Wang","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056584611","display_name":"Alex Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Alex Xiao","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074237839","display_name":"Jay Mahadeokar","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jay Mahadeokar","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073252960","display_name":"Xiaohui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Xiaohui Zhang","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069296252","display_name":"Chunxi Liu","orcid":"https://orcid.org/0000-0001-5441-9374"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Chunxi Liu","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343439","display_name":"Ke Li","orcid":"https://orcid.org/0000-0001-5467-7218"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ke Li","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047358828","display_name":"Yuan Shangguan","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yuan Shangguan","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034208747","display_name":"Varun Nagaraja","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Varun Nagaraja","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066166549","display_name":"Ozlem Kalinli","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ozlem Kalinli","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113773386","display_name":"Mike Seltzer","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Mike Seltzer","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5103247973"],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":1.4613,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.83558594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8277","last_page":"8281"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9983000159263611,"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":0.8038830757141113},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6472557783126831},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6160986423492432},{"id":"https://openalex.org/keywords/dictation","display_name":"Dictation","score":0.6124298572540283},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5386853218078613},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.5313931703567505},{"id":"https://openalex.org/keywords/overlap\u2013add-method","display_name":"Overlap\u2013add method","score":0.5102596282958984},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46258899569511414},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4140145182609558},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38160523772239685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30760496854782104},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.1367127001285553},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13136526942253113},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08632022142410278},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.07799580693244934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8038830757141113},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6472557783126831},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6160986423492432},{"id":"https://openalex.org/C2779077324","wikidata":"https://www.wikidata.org/wiki/Q1087138","display_name":"Dictation","level":2,"score":0.6124298572540283},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5386853218078613},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.5313931703567505},{"id":"https://openalex.org/C181002996","wikidata":"https://www.wikidata.org/wiki/Q1611641","display_name":"Overlap\u2013add method","level":5,"score":0.5102596282958984},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46258899569511414},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4140145182609558},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38160523772239685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30760496854782104},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1367127001285553},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13136526942253113},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08632022142410278},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.07799580693244934},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"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/C76563020","wikidata":"https://www.wikidata.org/wiki/Q4817582","display_name":"Fractional Fourier transform","level":4,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747706","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2407080277","https://openalex.org/W2795138957","https://openalex.org/W2798657914","https://openalex.org/W2802023636","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2948981900","https://openalex.org/W2962760690","https://openalex.org/W2962778134","https://openalex.org/W2963250244","https://openalex.org/W2963403868","https://openalex.org/W2964089206","https://openalex.org/W2972818416","https://openalex.org/W2981857663","https://openalex.org/W2982413405","https://openalex.org/W2986922898","https://openalex.org/W3007328579","https://openalex.org/W3010476030","https://openalex.org/W3016010032","https://openalex.org/W3021515889","https://openalex.org/W3096702180","https://openalex.org/W3096888553","https://openalex.org/W3097558625","https://openalex.org/W3097777922","https://openalex.org/W3098649167","https://openalex.org/W3146288864","https://openalex.org/W3149509723","https://openalex.org/W3161873870","https://openalex.org/W3162665866","https://openalex.org/W3163907627","https://openalex.org/W4288024261","https://openalex.org/W4288088457","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6739901393","https://openalex.org/W6763608318","https://openalex.org/W6769557084","https://openalex.org/W6769806307","https://openalex.org/W6770251742","https://openalex.org/W6774970780"],"related_works":["https://openalex.org/W4372260258","https://openalex.org/W2267589039","https://openalex.org/W2369791303","https://openalex.org/W2759540840","https://openalex.org/W2369804796","https://openalex.org/W2133280289","https://openalex.org/W2360069155","https://openalex.org/W4254230825","https://openalex.org/W2169963286","https://openalex.org/W2919798019"],"abstract_inverted_index":{"This":[0,42],"paper":[1,80],"improves":[2,99],"the":[3,16,24,35,45,58,62,94,100,124],"streaming":[4,21],"transformer":[5,22],"transducer":[6],"for":[7,75],"speech":[8],"recognition":[9],"using":[10,61],"non-causal":[11,31,63],"convolution.":[12],"Many":[13],"works":[14],"apply":[15],"causal":[17,72],"convolution":[18,32,49,64],"to":[19,29,33,91],"improve":[20,93,127],"ignoring":[23],"lookahead":[25,39,46,66,133],"context.":[26],"We":[27],"propose":[28],"use":[30],"process":[34],"center":[36],"block":[37],"and":[38,50,54,84,147],"context":[40,47,67,88,111,118,134],"separately.":[41],"method":[43,113],"leverages":[44],"in":[48],"maintains":[51],"similar":[52,59],"training":[53],"decoding":[55],"efficiency.":[56],"Given":[57],"latency,":[60],"with":[65,132],"gives":[68],"better":[69],"accuracy":[70],"than":[71],"convolution,":[73],"especially":[74],"open-domain":[76,142],"dictation.":[77],"Besides,":[78],"this":[79],"applies":[81],"talking-head":[82,97],"attention":[83,98],"a":[85,128],"novel":[86],"history":[87,110,117],"compression":[89,112],"scheme":[90],"further":[92],"performance.":[95],"The":[96,109],"multi-head":[101],"self-attention":[102],"by":[103,135],"transferring":[104],"information":[105],"among":[106],"different":[107],"heads.":[108],"introduces":[114],"more":[115],"extended":[116],"compactly.":[119],"On":[120],"our":[121],"in-house":[122],"data,":[123],"proposed":[125],"methods":[126],"small":[129],"Emformer":[130],"baseline":[131],"relative":[136],"WERR":[137],"5.1%,":[138],"14.5%,":[139],"8.4%":[140],"on":[141],"dictation,":[143],"assistant":[144,148],"general":[145],"scenarios,":[146],"calling":[149],"scenarios":[150],"respectively.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}