{"id":"https://openalex.org/W3008549139","doi":"https://doi.org/10.1109/asru46091.2019.9003832","title":"Multilingual End-to-End Speech Translation","display_name":"Multilingual End-to-End Speech Translation","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008549139","doi":"https://doi.org/10.1109/asru46091.2019.9003832","mag":"3008549139"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003832","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070418792","display_name":"Kevin Duh","orcid":"https://orcid.org/0000-0001-8107-4383"},"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":"Kevin Duh","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"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/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":"Shinji Watanabe","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"570","last_page":"577"},"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9994999766349792,"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":0.8428696393966675},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7936137914657593},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6281216144561768},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.619590163230896},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.599744975566864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5404558777809143},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5311253070831299},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.46504083275794983},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45696112513542175},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.43057799339294434},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.42337095737457275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8428696393966675},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7936137914657593},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6281216144561768},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.619590163230896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.599744975566864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5404558777809143},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5311253070831299},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.46504083275794983},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45696112513542175},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43057799339294434},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.42337095737457275},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003832","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W179875071","https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1591801644","https://openalex.org/W1686810756","https://openalex.org/W1970890968","https://openalex.org/W1970987322","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2106440210","https://openalex.org/W2113106066","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2183341477","https://openalex.org/W2184135559","https://openalex.org/W2251743902","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2531207078","https://openalex.org/W2550821151","https://openalex.org/W2555745756","https://openalex.org/W2605131327","https://openalex.org/W2739883972","https://openalex.org/W2745785989","https://openalex.org/W2762715843","https://openalex.org/W2766219058","https://openalex.org/W2767906378","https://openalex.org/W2770394828","https://openalex.org/W2772556289","https://openalex.org/W2785350307","https://openalex.org/W2786835190","https://openalex.org/W2786891429","https://openalex.org/W2788652410","https://openalex.org/W2799316004","https://openalex.org/W2808682925","https://openalex.org/W2889330634","https://openalex.org/W2894835365","https://openalex.org/W2897726470","https://openalex.org/W2899716505","https://openalex.org/W2899773543","https://openalex.org/W2945700568","https://openalex.org/W2949328740","https://openalex.org/W2950057603","https://openalex.org/W2955541912","https://openalex.org/W2957558225","https://openalex.org/W2962778428","https://openalex.org/W2962784628","https://openalex.org/W2962835968","https://openalex.org/W2963027641","https://openalex.org/W2963216553","https://openalex.org/W2963247703","https://openalex.org/W2963292011","https://openalex.org/W2963403868","https://openalex.org/W2963779652","https://openalex.org/W2963819008","https://openalex.org/W2964121744","https://openalex.org/W2964161387","https://openalex.org/W2964172053","https://openalex.org/W2964308564","https://openalex.org/W2964309797","https://openalex.org/W2972448360","https://openalex.org/W3012492057","https://openalex.org/W3015703505","https://openalex.org/W4300558631","https://openalex.org/W4385245566","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6629717138","https://openalex.org/W6631362777","https://openalex.org/W6637373629","https://openalex.org/W6679434410","https://openalex.org/W6686282164","https://openalex.org/W6713762819","https://openalex.org/W6729684557","https://openalex.org/W6746683980","https://openalex.org/W6748215858","https://openalex.org/W6748534668","https://openalex.org/W6754599529","https://openalex.org/W6765485641","https://openalex.org/W6775053297","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2883671469","https://openalex.org/W2990025607","https://openalex.org/W2728761353","https://openalex.org/W3045103338","https://openalex.org/W3007142233","https://openalex.org/W4399356803","https://openalex.org/W3177132412","https://openalex.org/W3198731777"],"abstract_inverted_index":{"In":[0],"this":[1,53,134],"paper,":[2],"we":[3],"propose":[4],"a":[5,32,109,114],"simple":[6],"yet":[7],"effective":[8],"framework":[9],"for":[10,44],"multilingual":[11,37,71,89,103,136],"end-to-end":[12,63,72,90],"speech":[13,18,46],"translation":[14,51],"(ST),":[15],"in":[16,20,74,97,108,133],"which":[17],"utterances":[19],"source":[21],"languages":[22,30],"are":[23,59,126],"directly":[24],"translated":[25],"to":[26,41,61,113,129],"the":[27,55,62,68,124],"desired":[28],"target":[29],"with":[31,81],"universal":[33],"sequence-to-sequence":[34],"architecture.":[35],"While":[36],"models":[38,92],"have":[39],"shown":[40],"be":[42],"useful":[43],"automatic":[45],"recognition":[47],"(ASR)":[48],"and":[49,78,123],"machine":[50],"(MT),":[52],"is":[54,105],"first":[56],"time":[57],"they":[58],"applied":[60],"ST":[64,73,91,137],"problem.":[65],"We":[66,85],"show":[67],"effectiveness":[69],"of":[70,102,120],"two":[75],"scenarios:":[76],"one-to-many":[77],"many-to-many":[79],"translations":[80],"publicly":[82,127],"available":[83,128],"data.":[84],"experimentally":[86],"confirm":[87],"that":[88],"significantly":[93],"outperform":[94],"bilingual":[95],"ones":[96],"both":[98],"scenarios.":[99],"The":[100],"generalization":[101],"training":[104],"also":[106],"evaluated":[107],"transfer":[110],"learning":[111],"scenario":[112],"very":[115],"low-resource":[116],"language":[117],"pair.":[118],"All":[119],"our":[121],"codes":[122],"database":[125],"encourage":[130],"further":[131],"research":[132],"emergent":[135],"topic":[138],"<sup":[139],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[140],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">11</sup>":[141],"Available":[142],"at":[143],"https://github.com/espnet/espnet..":[144]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}