{"id":"https://openalex.org/W3100370880","doi":"https://doi.org/10.1109/asru51503.2021.9688026","title":"Enabling Zero-Shot Multilingual Spoken Language Translation with Language-Specific Encoders and Decoders","display_name":"Enabling Zero-Shot Multilingual Spoken Language Translation with Language-Specific Encoders and Decoders","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3100370880","doi":"https://doi.org/10.1109/asru51503.2021.9688026","mag":"3100370880"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688026","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.01097","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032308508","display_name":"Carlos Escolano","orcid":"https://orcid.org/0000-0002-1653-7780"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Carlos Escolano","raw_affiliation_strings":["TALP Research Center, Universitat Polit&#x00E8;cnica de Catalunya,Barcelona"],"affiliations":[{"raw_affiliation_string":"TALP Research Center, Universitat Polit&#x00E8;cnica de Catalunya,Barcelona","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074210163","display_name":"Marta R. Costa\u2010juss\u00e0","orcid":"https://orcid.org/0000-0002-5703-520X"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Marta R. Costa-jussa","raw_affiliation_strings":["TALP Research Center, Universitat Polit&#x00E8;cnica de Catalunya,Barcelona"],"affiliations":[{"raw_affiliation_string":"TALP Research Center, Universitat Polit&#x00E8;cnica de Catalunya,Barcelona","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004224082","display_name":"Jos\u00e9 A. R. Fonollosa","orcid":"https://orcid.org/0000-0001-9513-7939"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose A. R. Fonollosa","raw_affiliation_strings":["TALP Research Center, Universitat Polit&#x00E8;cnica de Catalunya,Barcelona"],"affiliations":[{"raw_affiliation_string":"TALP Research Center, Universitat Polit&#x00E8;cnica de Catalunya,Barcelona","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023990637","display_name":"Carlos Segura","orcid":"https://orcid.org/0000-0002-5431-5927"},"institutions":[{"id":"https://openalex.org/I4210134591","display_name":"Telefonica Research and Development","ror":"https://ror.org/03qgzzb04","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210097190","https://openalex.org/I4210134591"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carlos Segura","raw_affiliation_strings":["Telef&#x00F3;nica I+D,Barcelona"],"affiliations":[{"raw_affiliation_string":"Telef&#x00F3;nica I+D,Barcelona","institution_ids":["https://openalex.org/I4210134591"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032308508"],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":0.7613,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73144811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"5","issue":null,"first_page":"694","last_page":"701"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9987999796867371,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8603596687316895},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7910628318786621},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6469792127609253},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5916301608085632},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.5848339796066284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5601927042007446},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4977264702320099},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4707152247428894},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4695347547531128},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.46793267130851746},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4395405948162079},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4308048188686371},{"id":"https://openalex.org/keywords/multilingualism","display_name":"Multilingualism","score":0.4218888282775879},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4146469831466675},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1817896068096161},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13622233271598816}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8603596687316895},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7910628318786621},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6469792127609253},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5916301608085632},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.5848339796066284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5601927042007446},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4977264702320099},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4707152247428894},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4695347547531128},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.46793267130851746},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4395405948162079},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4308048188686371},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.4218888282775879},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4146469831466675},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1817896068096161},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13622233271598816},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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},{"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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":4,"locations":[{"id":"doi:10.1109/asru51503.2021.9688026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688026","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"},{"id":"pmh:oai:arXiv.org:2011.01097","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01097","pdf_url":"https://arxiv.org/pdf/2011.01097","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3100370880","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.01097","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.01097","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.01097","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.01097","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01097","pdf_url":"https://arxiv.org/pdf/2011.01097","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3100370880.pdf","grobid_xml":"https://content.openalex.org/works/W3100370880.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W2101105183","https://openalex.org/W2124807415","https://openalex.org/W2270190199","https://openalex.org/W2550821151","https://openalex.org/W2889326414","https://openalex.org/W2892009249","https://openalex.org/W2926063217","https://openalex.org/W2962784628","https://openalex.org/W2963403868","https://openalex.org/W2964089206","https://openalex.org/W2970761781","https://openalex.org/W2970925270","https://openalex.org/W2971840980","https://openalex.org/W2972630480","https://openalex.org/W2974587205","https://openalex.org/W2978099976","https://openalex.org/W2982180741","https://openalex.org/W3008125272","https://openalex.org/W3008549139","https://openalex.org/W3017208877","https://openalex.org/W3046226013","https://openalex.org/W3112092703","https://openalex.org/W3118554287","https://openalex.org/W6600880057","https://openalex.org/W6691646088","https://openalex.org/W6769553789","https://openalex.org/W6773238793","https://openalex.org/W6776211976","https://openalex.org/W6787407267","https://openalex.org/W6788861718","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3019421297","https://openalex.org/W3107826490","https://openalex.org/W3099782249","https://openalex.org/W2936774411","https://openalex.org/W2971152344","https://openalex.org/W2949911645","https://openalex.org/W3213179206","https://openalex.org/W2951184134","https://openalex.org/W3202167223","https://openalex.org/W2552124255","https://openalex.org/W3112158532","https://openalex.org/W3201959471","https://openalex.org/W3088089622","https://openalex.org/W3211989872","https://openalex.org/W2912095972","https://openalex.org/W2891844856","https://openalex.org/W3173767661","https://openalex.org/W3112092703","https://openalex.org/W2963403868","https://openalex.org/W2945700568"],"abstract_inverted_index":{"Current":[0],"end-to-end":[1,142],"approaches":[2,26],"to":[3,46,66,88,97,128],"Spoken":[4],"Language":[5],"Translation":[6,24],"(SLT)":[7],"rely":[8,27],"on":[9,28,43,71,78,132,140],"limited":[10],"training":[11,69],"resources,":[12],"especially":[13],"for":[14,106,116],"multilingual":[15],"settings.":[16],"On":[17],"the":[18,47,57,85,89,118,133,141],"other":[19],"hand,":[20],"Multilingual":[21,50],"Neural":[22],"Machine":[23],"(MultiNMT)":[25],"higher-quality":[29],"and":[30,62,73,136],"more":[31],"massive":[32],"data":[33,61],"sets.":[34],"Our":[35,53,76],"proposed":[36,134],"method":[37,54],"extends":[38],"a":[39,98],"MultiNMT":[40,74,90],"architecture":[41,91,135],"based":[42],"language-specific":[44],"encoders-decoders":[45],"task":[48],"of":[49],"SLT":[51],"(Multi-SLT).":[52],"entirely":[55],"eliminates":[56],"dependency":[58],"from":[59],"MultiSLT":[60],"it":[63],"is":[64],"able":[65],"translate":[67],"while":[68,103],"only":[70],"ASR":[72],"data.":[75],"experiments":[77],"four":[79],"different":[80],"languages":[81],"show":[82],"that":[83],"coupling":[84,117],"speech":[86,119],"encoder":[87],"produces":[92,124],"similar":[93],"quality":[94],"translations":[95],"compared":[96],"bilingual":[99],"baseline":[100],"(\u00b10.2":[101],"BLEU)":[102],"effectively":[104],"allowing":[105],"zero-shot":[107],"MultiSLT.":[108],"Additionally,":[109],"we":[110],"propose":[111],"using":[112],"an":[113],"Adapter":[114,122],"module":[115,123],"inputs.":[120],"This":[121],"consistent":[125],"improvements":[126],"up":[127],"+6":[129],"BLEU":[130,138],"points":[131],"+1":[137],"point":[139],"baseline.":[143]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
