{"id":"https://openalex.org/W4391631670","doi":"https://doi.org/10.1109/icasspw62465.2024.10626683","title":"Cross-Lingual Transfer Learning for Low-Resource Speech Translation","display_name":"Cross-Lingual Transfer Learning for Low-Resource Speech Translation","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4391631670","doi":"https://doi.org/10.1109/icasspw62465.2024.10626683"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"article","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/A5035187454","display_name":"Sameer Khurana","orcid":"https://orcid.org/0000-0002-3182-1085"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Sameer Khurana","raw_affiliation_strings":["Mitsubishi Electric Research Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Lab","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067313233","display_name":"Nauman Dawalatabad","orcid":"https://orcid.org/0000-0003-1592-6300"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nauman Dawalatabad","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025212823","display_name":"Antoine Laurent","orcid":"https://orcid.org/0000-0002-2653-1008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antoine Laurent","raw_affiliation_strings":["LIUM University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIUM University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101645455","display_name":"Luis Vicente","orcid":"https://orcid.org/0000-0003-4391-5203"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luis Vicente","raw_affiliation_strings":["University of Zaragoza"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zaragoza","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069847313","display_name":"Pablo Gimeno","orcid":"https://orcid.org/0000-0002-3142-0708"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pablo Gimeno","raw_affiliation_strings":["University of Zaragoza"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zaragoza","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053658389","display_name":"Victoria Mingote","orcid":"https://orcid.org/0000-0002-3505-0249"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Victoria Mingote","raw_affiliation_strings":["University of Zaragoza"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zaragoza","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5035187454"],"corresponding_institution_ids":["https://openalex.org/I4210133125"],"apc_list":null,"apc_paid":null,"fwci":1.2711,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81712308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"670","last_page":"674"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9786999821662903,"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":0.9786999821662903,"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":0.9491000175476074,"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":0.7613989114761353},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5281130075454712},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5214352011680603},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45140019059181213},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4347696900367737},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4143602252006531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.382537841796875},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07186248898506165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613989114761353},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5281130075454712},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5214352011680603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45140019059181213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4347696900367737},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4143602252006531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.382537841796875},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07186248898506165},{"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/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/icasspw62465.2024.10626683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2407080277","https://openalex.org/W2560647685","https://openalex.org/W3001434439","https://openalex.org/W3030437843","https://openalex.org/W3032433061","https://openalex.org/W3036601975","https://openalex.org/W3039695075","https://openalex.org/W3096918678","https://openalex.org/W3101498587","https://openalex.org/W3173767661","https://openalex.org/W3213029956","https://openalex.org/W4221155340","https://openalex.org/W4286359908","https://openalex.org/W6771467084","https://openalex.org/W6773238793","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6810259195"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W2775554247","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4386247111","https://openalex.org/W4327642362","https://openalex.org/W2587014613"],"abstract_inverted_index":{"The":[0,26],"paper":[1],"presents":[2],"a":[3,29,110],"novel":[4],"three-step":[5,64],"transfer":[6,12,38,66,73],"learning":[7,39,67],"framework":[8,40,68,80],"for":[9,106],"enhancing":[10],"cross-lingual":[11,37,65,72],"from":[13],"high-":[14],"to":[15,46],"low-resource":[16,84,107],"languages":[17],"in":[18,50,77,102,113],"the":[19,34,51,70,78,96,114],"downstream":[20],"application":[21],"of":[22],"Automatic":[23],"Speech":[24],"Translation.":[25],"approach":[27],"integrates":[28],"semantic":[30,48],"knowledge-distillation":[31],"step":[32,44],"into":[33],"existing":[35],"two-step":[36],"XLS-R.":[41],"This":[42],"extra":[43],"aims":[45],"encode":[47],"knowledge":[49],"multilingual":[52],"speech":[53],"encoder":[54],"pre-trained":[55],"via":[56],"Self-Supervised":[57],"Learning":[58],"using":[59],"unlabeled":[60],"speech.":[61],"Our":[62],"proposed":[63],"addresses":[69],"large":[71],"gap":[74],"(TRFGap)":[75],"observed":[76],"XLS-R":[79],"between":[81],"high-resource":[82],"and":[83,93,109],"languages.":[85],"We":[86],"validate":[87],"our":[88],"proposal":[89],"through":[90],"extensive":[91],"experiments":[92],"comparisons":[94],"on":[95],"CoVoST-2":[97],"benchmark,":[98],"showing":[99],"significant":[100],"improvements":[101],"translation":[103],"performance,":[104],"especially":[105],"languages,":[108],"notable":[111],"reduction":[112],"TRFGap.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-19T08:33:51.333923","created_date":"2025-10-10T00:00:00"}