{"id":"https://openalex.org/W2936969148","doi":"https://doi.org/10.1162/tacl_a_00270","title":"Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation","display_name":"Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation","publication_year":2019,"publication_date":"2019-06-19","ids":{"openalex":"https://openalex.org/W2936969148","doi":"https://doi.org/10.1162/tacl_a_00270","mag":"2936969148"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00270","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00270","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00270/1923092/tacl_a_00270.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00270/1923092/tacl_a_00270.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024736091","display_name":"Matthias Sperber","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Sperber","raw_affiliation_strings":["Karlsruhe Institute of Technology, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789"},"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":true,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046084081","display_name":"Jan Niehues","orcid":"https://orcid.org/0000-0002-4231-6543"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Niehues","raw_affiliation_strings":["Karlsruhe Institute of Technology, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110453805","display_name":"Alex Waibel","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"]},{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE","US"],"is_corresponding":true,"raw_author_name":"Alex Waibel","raw_affiliation_strings":["Carnegie Mellon University, USA","Karlsruhe Institute of Technology, Germany"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Karlsruhe Institute of Technology, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068811427","https://openalex.org/A5110453805"],"corresponding_institution_ids":["https://openalex.org/I102335020","https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":10.6412,"has_fulltext":false,"cited_by_count":94,"citation_normalized_percentile":{"value":0.98577008,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"7","issue":null,"first_page":"313","last_page":"325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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":0.9998999834060669,"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":0.9944000244140625,"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":0.8915349841117859},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.697494626045227},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6918782591819763},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6434568166732788},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5785716772079468},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5766490697860718},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.550632119178772},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5301923155784607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5272996425628662},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.4947752356529236},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.47808074951171875},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4658221900463104},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4365648031234741}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8915349841117859},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.697494626045227},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6918782591819763},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6434568166732788},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5785716772079468},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5766490697860718},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.550632119178772},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5301923155784607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5272996425628662},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.4947752356529236},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.47808074951171875},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4658221900463104},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4365648031234741},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00270","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00270","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00270/1923092/tacl_a_00270.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ec0209656f3c4c0cb272740ed21cee1d","is_oa":true,"landing_page_url":"https://doaj.org/article/ec0209656f3c4c0cb272740ed21cee1d","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 7, Pp 313-325 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00270","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00270","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00270/1923092/tacl_a_00270.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2936969148.pdf","grobid_xml":"https://content.openalex.org/works/W2936969148.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W569478347","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2183341477","https://openalex.org/W2327501763","https://openalex.org/W2419539795","https://openalex.org/W2466918907","https://openalex.org/W2530876040","https://openalex.org/W2595840341","https://openalex.org/W2605131327","https://openalex.org/W2620290161","https://openalex.org/W2620507731","https://openalex.org/W2768066693","https://openalex.org/W2785350307","https://openalex.org/W2792296443","https://openalex.org/W2962680099","https://openalex.org/W2962717763","https://openalex.org/W2963086938","https://openalex.org/W2963266340","https://openalex.org/W2963303028","https://openalex.org/W2963551569","https://openalex.org/W2963779652","https://openalex.org/W2963834942","https://openalex.org/W2964084097","https://openalex.org/W2964172053","https://openalex.org/W2964308564","https://openalex.org/W3012492057","https://openalex.org/W3163547718","https://openalex.org/W4300558631"],"related_works":["https://openalex.org/W2990025607","https://openalex.org/W3045103338","https://openalex.org/W3007142233","https://openalex.org/W2916997151","https://openalex.org/W3037186962","https://openalex.org/W2949174760","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165","https://openalex.org/W3177132412"],"abstract_inverted_index":{"Speech":[0],"translation":[1,24,99,109,187],"has":[2],"traditionally":[3],"been":[4,77],"approached":[5],"through":[6,127],"cascaded":[7,118],"models":[8,110,154,180],"consisting":[9],"of":[10,18,37,57,90,150,203],"a":[11,16,22,42,55,140,144,200,204],"speech":[12,95,108,163],"recognizer":[13],"trained":[14,26,49,86],"on":[15,27,54,64,87],"corpus":[17,56],"transcribed":[19],"speech,":[20],"and":[21,74,97,120,186,189,217],"machine":[23,98],"system":[25],"parallel":[28],"texts.":[29],"Several":[30],"recent":[31],"works":[32],"have":[33,75],"shown":[34],"the":[35,39,66,69,80,148,159,168],"feasibility":[36],"collapsing":[38],"cascade":[40,67],"into":[41,183],"single,":[43],"direct":[44,70,107,229],"model":[45,71,205,212],"that":[46,83,106,178,194],"can":[47],"be":[48],"in":[50,199],"an":[51,191],"end-to-end":[52],"fashion":[53],"translated":[58],"speech.":[59],"However,":[60],"experiments":[61],"are":[62,85,131],"inconclusive":[63],"whether":[65],"or":[68],"is":[72,218],"stronger,":[73],"only":[76],"conducted":[78],"under":[79],"unrealistic":[81],"assumption":[82],"both":[84],"equal":[88],"amounts":[89],"data,":[91,136],"ignoring":[92],"other":[93],"available":[94],"recognition":[96,185],"corpora.":[100],"In":[101],"this":[102],"paper,":[103],"we":[104,146],"demonstrate":[105],"require":[111],"more":[112,226],"data":[113,126,224],"to":[114,164,172,220],"perform":[115],"well":[116],"than":[117,228],"models,":[119],"although":[121],"they":[122,130],"allow":[123],"including":[124],"auxiliary":[125,222],"multi-task":[128],"training,":[129],"poor":[132],"at":[133,139],"exploiting":[134],"such":[135,179],"putting":[137],"them":[138],"severe":[141],"disadvantage.":[142],"As":[143],"remedy,":[145],"propose":[147,190],"use":[149],"end-":[151],"to-end":[152],"trainable":[153],"with":[155,206],"two":[156,207],"attention":[157,208],"mechanisms,":[158],"first":[160],"establishing":[161],"source":[162,165,171],"text":[166,174],"alignments,":[167],"second":[169],"modeling":[170],"target":[173],"alignment.":[175],"We":[176],"show":[177],"naturally":[181],"decompose":[182],"multi-task\u2013trainable":[184],"tasks":[188],"attention-passing":[192],"technique":[193],"alleviates":[195],"error":[196],"propagation":[197],"issues":[198],"previous":[201],"formulation":[202],"stages.":[209],"Our":[210],"proposed":[211],"outperforms":[213],"all":[214],"examined":[215],"baselines":[216],"able":[219],"exploit":[221],"training":[223],"much":[225],"effectively":[227],"attentional":[230],"models.":[231]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}