{"id":"https://openalex.org/W3162665866","doi":"https://doi.org/10.1109/icassp39728.2021.9414560","title":"Emformer: Efficient Memory Transformer Based Acoustic Model for Low Latency Streaming Speech Recognition","display_name":"Emformer: Efficient Memory Transformer Based Acoustic Model for Low Latency Streaming Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162665866","doi":"https://doi.org/10.1109/icassp39728.2021.9414560","mag":"3162665866"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414560","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":"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/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":false,"raw_author_name":"Yangyang Shi","raw_affiliation_strings":["Facebook AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"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/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":"Yongqiang Wang","raw_affiliation_strings":["Facebook AI"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087421101","display_name":"Ching-Feng Yeh","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":"Ching-Feng Yeh","raw_affiliation_strings":["Facebook AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051075420","display_name":"Julian Chan","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":"Julian Chan","raw_affiliation_strings":["Facebook AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"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/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":"Frank Zhang","raw_affiliation_strings":["Facebook AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103098852","display_name":"Duc Le","orcid":"https://orcid.org/0000-0001-9490-2563"},"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":"Duc Le","raw_affiliation_strings":["Facebook AI"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":16.2647,"has_fulltext":false,"cited_by_count":124,"citation_normalized_percentile":{"value":0.99446609,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6783","last_page":"6787"},"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":0.9988999962806702,"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":0.9984999895095825,"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":0.7587130069732666},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6301689743995667},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.62009197473526},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.49743106961250305},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.492107093334198},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.26006561517715454},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12405449151992798},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11784517765045166},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09847047924995422},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09141159057617188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587130069732666},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6301689743995667},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.62009197473526},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.49743106961250305},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.492107093334198},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26006561517715454},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12405449151992798},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11784517765045166},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09847047924995422},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09141159057617188}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414560","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W2131342762","https://openalex.org/W2407080277","https://openalex.org/W2802023636","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2911291251","https://openalex.org/W2913718171","https://openalex.org/W2936774411","https://openalex.org/W2962778134","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964089206","https://openalex.org/W2964110616","https://openalex.org/W2964121744","https://openalex.org/W2972818416","https://openalex.org/W2981857663","https://openalex.org/W2982413405","https://openalex.org/W3007328579","https://openalex.org/W3008525923","https://openalex.org/W3015960524","https://openalex.org/W3015974384","https://openalex.org/W3016010032","https://openalex.org/W3021515889","https://openalex.org/W3025165719","https://openalex.org/W3082274269","https://openalex.org/W3096702180","https://openalex.org/W3096888553","https://openalex.org/W3097075707","https://openalex.org/W3097558625","https://openalex.org/W3097777922","https://openalex.org/W3097973766","https://openalex.org/W3161873870","https://openalex.org/W4288088457","https://openalex.org/W4288089799","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6679429981","https://openalex.org/W6713762819","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6769557084","https://openalex.org/W6769627184","https://openalex.org/W6769806307","https://openalex.org/W6784418856"],"related_works":["https://openalex.org/W2044408773","https://openalex.org/W2130717063","https://openalex.org/W4383605217","https://openalex.org/W2533508831","https://openalex.org/W48790062","https://openalex.org/W2742699532","https://openalex.org/W4281389974","https://openalex.org/W1911859126","https://openalex.org/W2325482719","https://openalex.org/W2397926608"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,23,127],"efficient":[4],"memory":[5,25,92],"transformer":[6,93],"Emformer":[7,49,76,95,133,155],"for":[8,38,45],"low":[9,59,123],"latency":[10,60,72,124,129,151],"streaming":[11],"speech":[12],"recognition.":[13],"In":[14],"Emformer,":[15],"the":[16,36,39,46,145,149],"long-range":[17],"history":[18],"context":[19],"is":[20],"distilled":[21],"into":[22],"augmented":[24,91],"bank":[26],"to":[27,57],"reduce":[28],"self-attention\u2019s":[29],"computation":[30,37],"complexity.":[31],"A":[32],"cache":[33],"mechanism":[34],"saves":[35],"key":[40],"and":[41,82,101,117,139,152,161,165],"value":[42],"in":[43,55,108],"self-attention":[44],"left":[47],"context.":[48],"applies":[50],"a":[51,88,122],"parallelized":[52],"block":[53],"processing":[54],"training":[56,99],"support":[58],"models.":[61],"We":[62],"carry":[63],"out":[64],"experiments":[65],"on":[66,80,84,115,119,137,141,163],"benchmark":[67],"LibriSpeech":[68],"data.":[69],"Under":[70],"average":[71,128],"of":[73,130],"960":[74],"ms,":[75,132],"gets":[77,96,156],"WER":[78,112,135,158],"2.50%":[79],"test-clean":[81,116,138,164],"5.62%":[83],"test-other.":[85,120,142],"Comparing":[86,143],"with":[87,110,126,144,148],"strong":[89],"baseline":[90,147],"(AM-TRF),":[94],"4.6":[97],"folds":[98],"speedup":[100],"18%":[102],"relative":[103,111,157],"real-time":[104],"factor":[105],"(RTF)":[106],"reduction":[107,113,159],"decoding":[109],"17%":[114],"9%":[118,160],"For":[121],"scenario":[125],"80":[131],"achieves":[134],"3.01%":[136],"7.09%":[140],"LSTM":[146],"same":[150],"model":[153],"size,":[154],"16%":[162],"test-other,":[166],"respectively.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":23}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}