{"id":"https://openalex.org/W3198492054","doi":"https://doi.org/10.21437/interspeech.2021-1953","title":"Multi-Mode Transformer Transducer with Stochastic Future Context","display_name":"Multi-Mode Transformer Transducer with Stochastic Future Context","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198492054","doi":"https://doi.org/10.21437/interspeech.2021-1953","mag":"3198492054"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1953","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5052377938","display_name":"Kwangyoun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kwangyoun Kim","raw_affiliation_strings":["ASAPP, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP, USA","institution_ids":["https://openalex.org/I1283576576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074393700","display_name":"Felix Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix Wu","raw_affiliation_strings":["ASAPP, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP, USA","institution_ids":["https://openalex.org/I1283576576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006917911","display_name":"Prashant Sridhar","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashant Sridhar","raw_affiliation_strings":["ASAPP, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP, USA","institution_ids":["https://openalex.org/I1283576576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106859201","display_name":"Kyu J. Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyu J. Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["ASAPP, USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP, USA","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1827","last_page":"1831"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9879000186920166,"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/T10860","display_name":"Speech and Audio Processing","score":0.986299991607666,"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/transducer","display_name":"Transducer","score":0.7401921153068542},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5722881555557251},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.564007043838501},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4500303268432617},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3559856414794922},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.34963899850845337},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.3231297731399536},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2210695743560791},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15621572732925415},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.14347681403160095},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.11442959308624268}],"concepts":[{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.7401921153068542},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5722881555557251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.564007043838501},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4500303268432617},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3559856414794922},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.34963899850845337},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3231297731399536},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2210695743560791},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15621572732925415},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.14347681403160095},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.11442959308624268},{"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:10.21437/interspeech.2021-1953","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W2605141709","https://openalex.org/W2739883972","https://openalex.org/W2766219058","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963211739","https://openalex.org/W2963242190","https://openalex.org/W3008898571","https://openalex.org/W3015995734","https://openalex.org/W3016010032","https://openalex.org/W3092122846","https://openalex.org/W3093579165","https://openalex.org/W3094667432","https://openalex.org/W3095687747","https://openalex.org/W3095697114","https://openalex.org/W3097777922","https://openalex.org/W3125815078","https://openalex.org/W3162649911","https://openalex.org/W3163203022","https://openalex.org/W4288088457","https://openalex.org/W4294619417","https://openalex.org/W4300003935","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2383068986","https://openalex.org/W2090275562","https://openalex.org/W3152005513","https://openalex.org/W2020960496","https://openalex.org/W1266100159","https://openalex.org/W2034887142","https://openalex.org/W2088920587","https://openalex.org/W2139162221","https://openalex.org/W2092329823","https://openalex.org/W2864363823"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,11],"recognition":[2],"(ASR)":[3],"models":[4,44],"make":[5],"fewer":[6],"errors":[7],"when":[8,108],"more":[9,54],"surrounding":[10],"information":[12],"is":[13,57,112],"presented":[14],"as":[15,77],"context.Unfortunately,":[16],"acquiring":[17],"a":[18,53,60,91,109,138,160,168],"larger":[19,92],"future":[20,101,122],"context":[21,102,123],"leads":[22],"to":[23,34,41,58,76,103],"higher":[24,105],"latency.There":[25],"exists":[26],"an":[27],"inevitable":[28],"trade-off":[29],"between":[30],"speed":[31],"and":[32,45,107,154],"accuracy.Na\u00efvely,":[33],"fit":[35],"different":[36,71,176],"latency":[37,68,86,93,110,177],"requirements,":[38],"people":[39],"have":[40,59],"store":[42],"multiple":[43],"pick":[46],"the":[47,51,96,115],"best":[48],"one":[49,144],"under":[50],"constraints.Instead,":[52],"desirable":[55],"approach":[56],"single":[61],"model":[62,82,97,116,163],"that":[63,142,159],"can":[64,83,98,117],"dynamically":[65],"adjust":[66],"its":[67],"based":[69],"on":[70,121,152],"constraints,":[72],"which":[73],"we":[74,133,157],"refer":[75],"Multimode":[78],"ASR.A":[79],"Multi-mode":[80,131,161],"ASR":[81,162],"fulfill":[84],"various":[85],"requirements":[87],"during":[88],"inference":[89],"-when":[90],"becomes":[94],"acceptable,":[95],"process":[99],"longer":[100],"achieve":[104,126],"accuracy":[106],"budget":[111],"not":[113,166],"flexible,":[114],"be":[118],"less":[119],"dependent":[120],"but":[124],"still":[125],"reliable":[127],"accuracy.In":[128],"pursuit":[129],"of":[130,170],"ASR,":[132],"propose":[134],"Stochastic":[135],"Future":[136],"Context,":[137],"simple":[139],"training":[140],"procedure":[141],"samples":[143],"streaming":[145,172],"configuration":[146],"in":[147],"each":[148],"iteration.Through":[149],"extensive":[150],"experiments":[151],"AISHELL-1":[153],"Lib-riSpeech":[155],"datasets,":[156],"show":[158],"rivals,":[164],"if":[165],"surpasses,":[167],"set":[169],"competitive":[171],"baselines":[173],"trained":[174],"with":[175],"budgets.":[178]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}