{"id":"https://openalex.org/W4226054021","doi":"https://doi.org/10.1109/asru51503.2021.9687894","title":"Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates","display_name":"Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4226054021","doi":"https://doi.org/10.1109/asru51503.2021.9687894"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687894","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5040282669","display_name":"Hirofumi Inaguma","orcid":"https://orcid.org/0000-0003-0610-1251"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["Kyoto University,Japan","Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068873086","display_name":"Siddharth Dalmia","orcid":"https://orcid.org/0000-0003-0437-5988"},"institutions":[{"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":"Siddharth Dalmia","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021201726","display_name":"Brian Yan","orcid":null},"institutions":[{"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":"Brian Yan","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"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/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":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"922","last_page":"929"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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":0.8365139961242676},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.8279070854187012},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6960805654525757},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6168055534362793},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5896501541137695},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5088151097297668},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4436696171760559},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.43454238772392273},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42980140447616577},{"id":"https://openalex.org/keywords/soft-decision-decoder","display_name":"Soft-decision decoder","score":0.4107985198497772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3929438292980194},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29344600439071655},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.27061861753463745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8365139961242676},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8279070854187012},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6960805654525757},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6168055534362793},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5896501541137695},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5088151097297668},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4436696171760559},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.43454238772392273},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42980140447616577},{"id":"https://openalex.org/C185588885","wikidata":"https://www.wikidata.org/wiki/Q7553811","display_name":"Soft-decision decoder","level":3,"score":0.4107985198497772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3929438292980194},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29344600439071655},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.27061861753463745},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9687894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687894","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W2016589492","https://openalex.org/W2043701535","https://openalex.org/W2058094241","https://openalex.org/W2113106066","https://openalex.org/W2124807415","https://openalex.org/W2127141656","https://openalex.org/W2296073425","https://openalex.org/W2407080277","https://openalex.org/W2605131327","https://openalex.org/W2766219058","https://openalex.org/W2785350307","https://openalex.org/W2786891429","https://openalex.org/W2936774411","https://openalex.org/W2936969148","https://openalex.org/W2938973646","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W2963532001","https://openalex.org/W2963779652","https://openalex.org/W2964172053","https://openalex.org/W2972448360","https://openalex.org/W2972780808","https://openalex.org/W2972818416","https://openalex.org/W2988975212","https://openalex.org/W2989224798","https://openalex.org/W2997436923","https://openalex.org/W2998386507","https://openalex.org/W3007142233","https://openalex.org/W3007328579","https://openalex.org/W3012492057","https://openalex.org/W3015783745","https://openalex.org/W3015960524","https://openalex.org/W3034571331","https://openalex.org/W3037217258","https://openalex.org/W3037625699","https://openalex.org/W3094903517","https://openalex.org/W3097030750","https://openalex.org/W3097301532","https://openalex.org/W3097438275","https://openalex.org/W3097777922","https://openalex.org/W3097882114","https://openalex.org/W3102811925","https://openalex.org/W3105669983","https://openalex.org/W3111562797","https://openalex.org/W3113676066","https://openalex.org/W3118578889","https://openalex.org/W3147414526","https://openalex.org/W3148986242","https://openalex.org/W3153583341","https://openalex.org/W3157233339","https://openalex.org/W3160622492","https://openalex.org/W3162249256","https://openalex.org/W3162431424","https://openalex.org/W3162899666","https://openalex.org/W3162919436","https://openalex.org/W3163793923","https://openalex.org/W3168212167","https://openalex.org/W3170787215","https://openalex.org/W3172862365","https://openalex.org/W3174501695","https://openalex.org/W3175809709","https://openalex.org/W3176382501","https://openalex.org/W3177132412","https://openalex.org/W3186672448","https://openalex.org/W3197140813","https://openalex.org/W4300558631","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6748215858","https://openalex.org/W6770250107","https://openalex.org/W6775053297","https://openalex.org/W6784050962","https://openalex.org/W6784364040","https://openalex.org/W6785130102","https://openalex.org/W6787040858","https://openalex.org/W6787135666","https://openalex.org/W6793772276","https://openalex.org/W6794247771","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4391547476","https://openalex.org/W2597809628"],"abstract_inverted_index":{"The":[0],"multi-decoder":[1],"(MD)":[2],"end-to-end":[3],"speech":[4,18],"translation":[5,10,41,179],"model":[6,32,70,172],"has":[7],"demonstrated":[8],"high":[9],"quality":[11,192],"by":[12,74,86,100,111],"searching":[13],"for":[14,51,59],"better":[15],"intermediate":[16,186],"automatic":[17],"recognition":[19],"(ASR)":[20],"decoder":[21,106,130],"states":[22],"as":[23],"hidden":[24],"intermediates":[25],"(HI).":[26],"It":[27],"is":[28,47],"a":[29,67,125],"two-pass":[30],"decoding":[31,45,77,164,195],"decomposing":[33],"the":[34,44,118,128,169,182],"overall":[35],"task":[36],"into":[37],"ASR":[38,88,105,129],"and":[39,107,117,135,161,175,185],"machine":[40],"sub-tasks.":[42],"However,":[43],"speed":[46,165],"not":[48],"fast":[49,68],"enough":[50],"real-world":[52],"applications":[53],"because":[54],"it":[55],"conducts":[56],"beam":[57],"search":[58],"both":[60],"sub-tasks":[61],"during":[62,133,140,148],"inference.":[63],"We":[64,90],"propose":[65,144],"Fast-MD,":[66],"MD":[69,171],"that":[71,156,167],"generates":[72],"HI":[73,99,110],"non-autoregressive":[75],"(NAR)":[76],"based":[78],"on":[79,137,152,173],"connectionist":[80],"temporal":[81],"classification":[82],"(CTC)":[83],"outputs":[84,139,147],"followed":[85],"an":[87,102],"decoder.":[89],"investigated":[91],"two":[92],"types":[93],"of":[94,168],"NAR":[95],"HI:":[96],"(1)":[97],"parallel":[98],"using":[101,112],"autoregressive":[103],"Transformer":[104],"(2)":[108],"masked":[109,120],"Mask-CTC,":[113],"which":[114],"combines":[115],"CTC":[116,138,146,187],"conditional":[119],"language":[121],"model.":[122],"To":[123],"reduce":[124],"mismatch":[126],"in":[127],"between":[131],"teacher-forcing":[132],"training":[134],"conditioning":[136],"testing,":[141],"we":[142],"also":[143],"sampling":[145],"training.":[149],"Experimental":[150],"evaluations":[151],"three":[153],"corpora":[154],"show":[155],"Fast-MD":[157],"achieved":[158],"about":[159],"2\u00d7":[160],"4\u00d7":[162],"faster":[163],"than":[166],"na\u00efve":[170],"GPU":[174],"CPU":[176],"with":[177],"comparable":[178],"quality.":[180],"Adopting":[181],"Conformer":[183],"encoder":[184],"loss":[188],"further":[189],"boosts":[190],"its":[191],"without":[193],"sacrificing":[194],"speed.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}