{"id":"https://openalex.org/W3162000275","doi":"https://doi.org/10.1109/icassp39728.2021.9414897","title":"Streaming Simultaneous Speech Translation with Augmented Memory Transformer","display_name":"Streaming Simultaneous Speech Translation with Augmented Memory Transformer","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162000275","doi":"https://doi.org/10.1109/icassp39728.2021.9414897","mag":"3162000275"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414897","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":"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/A5054878003","display_name":"Xutai Ma","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":true,"raw_author_name":"Xutai Ma","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","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/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongqiang Wang","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001927789","display_name":"Mohammad Javad Dousti","orcid":"https://orcid.org/0000-0002-8537-2916"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Javad Dousti","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112315093","display_name":"Philipp Koehn","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Philipp Koehn","raw_affiliation_strings":["Facebook","Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058915697","display_name":"Juan Pino","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Pino","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5054878003"],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":3.8073,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.94350565,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7523","last_page":"7527"},"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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.8306121826171875},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7889009714126587},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6869751214981079},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6449558734893799},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5046037435531616},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.49968481063842773},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.44412705302238464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3663426637649536},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10010749101638794}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8306121826171875},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7889009714126587},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6869751214981079},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6449558734893799},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5046037435531616},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.49968481063842773},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.44412705302238464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3663426637649536},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10010749101638794},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414897","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":29,"referenced_works":["https://openalex.org/W419376470","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W2089629691","https://openalex.org/W2121457870","https://openalex.org/W2419292002","https://openalex.org/W2466633577","https://openalex.org/W2529548870","https://openalex.org/W2941814890","https://openalex.org/W2945700568","https://openalex.org/W2951456627","https://openalex.org/W2952992734","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2975711469","https://openalex.org/W2995428172","https://openalex.org/W3034586846","https://openalex.org/W3037217258","https://openalex.org/W3096888553","https://openalex.org/W3115075512","https://openalex.org/W4385245566","https://openalex.org/W6614488691","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6717306297","https://openalex.org/W6739901393","https://openalex.org/W6761563299","https://openalex.org/W6768570733","https://openalex.org/W6784851026"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W2903810591","https://openalex.org/W3026554633","https://openalex.org/W2888520903","https://openalex.org/W2890256614","https://openalex.org/W2949454572","https://openalex.org/W3066373881","https://openalex.org/W2970247882","https://openalex.org/W4389523797"],"abstract_inverted_index":{"Transformer-based":[0],"models":[1],"have":[2,80],"achieved":[3],"state-of-the-art":[4],"performance":[5],"on":[6,49,96,146,167],"speech":[7,51,102,150],"translation":[8,69],"tasks.":[9],"However,":[10],"the":[11,31,37,40,46,53,63,68,72,97,105,147,164],"model":[12,166],"architecture":[13],"is":[14,23],"not":[15,108],"efficient":[16],"enough":[17],"for":[18],"streaming":[19,100,148],"scenarios":[20],"since":[21],"self-attention":[22],"computed":[24],"over":[25],"an":[26,129,136,160],"entire":[27],"input":[28,41,115],"sequence":[29],"and":[30,170,173],"computational":[32],"cost":[33],"grows":[34],"quadratically":[35],"with":[36,113,135,153,181],"length":[38],"of":[39,45,55,99,111,163],"sequence.":[42],"Nevertheless,":[43],"most":[44],"previous":[47],"work":[48],"simultaneous":[50,101],"translation,":[52,103],"task":[54,98,152],"generating":[56,67],"translations":[57],"from":[58],"partial":[59,114],"audio":[60],"input,":[61],"ignores":[62],"time":[64],"spent":[65],"in":[66,88],"when":[70],"analyzing":[71],"latency.":[73],"With":[74],"this":[75,92],"assumption,":[76],"a":[77,179,182],"system":[78],"may":[79],"good":[81],"latency":[82],"quality":[83],"trade-offs":[84],"but":[85,116],"be":[86],"inapplicable":[87],"real-time":[89],"scenarios.":[90],"In":[91],"paper,":[93],"we":[94,174],"focus":[95],"where":[104],"systems":[106],"are":[107,117],"only":[109],"capable":[110],"translating":[112],"also":[118],"able":[119],"to":[120,178],"handle":[121],"very":[122],"long":[123],"or":[124,155],"continuous":[125],"input.":[126],"We":[127,158],"propose":[128],"end-to-end":[130],"transformer-based":[131],"sequence-to-sequence":[132],"model,":[133],"equipped":[134],"augmented":[137],"memory":[138,171],"transformer":[139,180],"encoder,":[140],"which":[141],"has":[142],"shown":[143],"great":[144],"success":[145],"automatic":[149],"recognition":[151],"hybrid":[154],"transducer-based":[156],"models.":[157],"conduct":[159],"empirical":[161],"evaluation":[162],"proposed":[165],"segment,":[168],"context":[169],"sizes":[172],"compare":[175],"our":[176],"approach":[177],"unidirectional":[183],"mask.":[184],"<sup":[185],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[186],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[187]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
