{"id":"https://openalex.org/W4416798544","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249304","title":"Improving Speech-to-Speech Translation for Low-Resource Languages via Transfer Learning","display_name":"Improving Speech-to-Speech Translation for Low-Resource Languages via Transfer Learning","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798544","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249304"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5063631680","display_name":"Rui Zhou","orcid":"https://orcid.org/0009-0001-3573-7905"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Rui Zhou","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University,Sendai,Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University,Sendai,Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082389304","display_name":"Akinori Ito","orcid":"https://orcid.org/0000-0002-8835-7877"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akinori Ito","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University,Sendai,Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University,Sendai,Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University,Sendai,Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University,Sendai,Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063631680"],"corresponding_institution_ids":["https://openalex.org/I201537933"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20701074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"801","last_page":"806"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6310999989509583,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.6310999989509583,"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":0.19789999723434448,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.016100000590085983,"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/transfer-of-learning","display_name":"Transfer of learning","score":0.6166999936103821},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.614799976348877},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5940999984741211},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5412999987602234},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.46639999747276306},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.42730000615119934},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4025000035762787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.809499979019165},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6166999936103821},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.614799976348877},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5940999984741211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5856999754905701},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5701000094413757},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5412999987602234},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.46639999747276306},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45249998569488525},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4025000035762787},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C2779178101","wikidata":"https://www.wikidata.org/wiki/Q6987274","display_name":"Negative transfer","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C2777938197","wikidata":"https://www.wikidata.org/wiki/Q7834022","display_name":"Transfer of training","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2792175982","https://openalex.org/W2913818371","https://openalex.org/W2963532001","https://openalex.org/W2972495969","https://openalex.org/W2972892814","https://openalex.org/W3092424727","https://openalex.org/W3198429080","https://openalex.org/W3209059054","https://openalex.org/W4200475319","https://openalex.org/W4287854499","https://openalex.org/W4389681059","https://openalex.org/W4403826739"],"related_works":[],"abstract_inverted_index":{"End-to-end":[0],"Speech-to-Speech":[1],"Translation":[2],"(S2ST)":[3],"enables":[4],"direct":[5],"transformation":[6],"from":[7,96,113,125],"source":[8],"speech":[9,15],"in":[10,16,44],"one":[11],"language":[12,57],"to":[13,40,66,105,115,119,127,131,148],"target":[14],"another.":[17],"Still,":[18],"it":[19],"typically":[20],"requires":[21],"large-scale":[22],"parallel":[23],"data,":[24],"which":[25],"is":[26,173],"unavailable":[27],"for":[28,68,133,175],"many":[29],"low-resource":[30,45,69,135,177],"languages.":[31],"In":[32],"this":[33],"work,":[34],"we":[35],"investigate":[36],"transfer":[37,77,95,145],"learning":[38],"strategies":[39],"improve":[41,112],"S2ST":[42,53],"performance":[43,149],"settings.":[46],"Our":[47],"approach":[48],"involves":[49],"pretraining":[50],"a":[51],"multi-task":[52],"model":[54],"on":[55],"high-resource":[56],"pairs":[58,70],"(e.g.,":[59],"French-English,":[60],"German-English,":[61],"Spanish-English)":[62],"and":[63,87,122,129,137,153],"transferring":[64],"parameters":[65],"models":[67],"such":[71],"as":[72],"Italian-English.":[73],"We":[74],"evaluate":[75],"multiple":[76],"configurations,":[78],"including":[79],"full":[80],"S2UT":[81],"transfer,":[82,152,168],"auxiliary":[83,155],"ASR":[84,156],"module":[85],"sharing,":[86],"partial":[88],"encoder/decoder":[89],"reuse.":[90],"Experimental":[91],"results":[92],"demonstrate":[93],"that":[94,143,154,164],"French-English":[97],"consistently":[98],"yields":[99],"the":[100,134,171],"most":[101],"significant":[102],"gains,":[103],"owing":[104],"its":[106],"larger":[107],"data":[108],"volume.":[109],"BLEU":[110],"scores":[111],"10.41":[114],"13.77":[116],"(ES-EN),":[117],"9.70":[118],"12.15":[120],"(DE-EN),":[121],"more":[123,147],"notably":[124],"2.89":[126],"10.01":[128],"2.10":[130],"9.10":[132],"IT-EN":[136],"RU-EN":[138],"pairs.":[139],"Ablation":[140],"studies":[141],"show":[142],"encoder":[144],"contributes":[146],"than":[150],"decoder":[151],"modules":[157],"provide":[158],"limited":[159],"benefits.":[160],"These":[161],"findings":[162],"suggest":[163],"carefully":[165],"designed":[166],"structural":[167],"particularly":[169],"of":[170],"encoder,":[172],"crucial":[174],"effective":[176],"S2ST.":[178]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}