{"id":"https://openalex.org/W4416034636","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.524","title":"Dub-S2ST: Textless Speech-to-Speech Translation for Seamless Dubbing","display_name":"Dub-S2ST: Textless Speech-to-Speech Translation for Seamless Dubbing","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034636","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.524"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.524","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.524","pdf_url":"https://aclanthology.org/2025.findings-emnlp.524.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.524.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111556720","display_name":"Jeongsoo Choi","orcid":"https://orcid.org/0000-0002-5554-3657"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongsoo Choi","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101733121","display_name":"Jaehun Kim","orcid":"https://orcid.org/0000-0002-3200-0406"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehun Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29932008,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9871","last_page":"9881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5702999830245972,"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":0.5702999830245972,"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":0.07670000195503235,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.04540000110864639,"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/translation","display_name":"Translation (biology)","score":0.48489999771118164},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.2955999970436096},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2879999876022339},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2549000084400177},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.23520000278949738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5264999866485596},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.48489999771118164},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28769999742507935},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.23520000278949738},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2295999974012375}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.524","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.524","pdf_url":"https://aclanthology.org/2025.findings-emnlp.524.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.524","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.524","pdf_url":"https://aclanthology.org/2025.findings-emnlp.524.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4405674155","display_name":null,"funder_award_id":"2022-II220989","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034636.pdf","grobid_xml":"https://content.openalex.org/works/W4416034636.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,61,87,94,108],"cross-lingual":[4],"dubbing":[5,55],"system":[6],"that":[7,99,121,129],"translates":[8],"speech":[9,33,42,49,76,106],"from":[10],"one":[11],"language":[12],"to":[13,45,104],"another":[14],"while":[15,139],"preserving":[16],"key":[17],"characteristics":[18],"such":[19],"as":[20],"duration,":[21],"speaker":[22],"identity,":[23],"and":[24,50,82,126,136],"speaking":[25,137],"speed.Despite":[26],"the":[27,39,79,101,112,132],"strong":[28],"translation":[29,34,65,102,142],"quality":[30],"of":[31,41],"existing":[32],"approaches,":[35],"they":[36],"often":[37],"overlook":[38],"transfer":[40],"patterns,":[43],"leading":[44],"mismatches":[46],"with":[47,67,111,131],"source":[48,83],"limiting":[51],"their":[52],"suitability":[53],"for":[54],"applications.To":[56],"address":[57],"this,":[58],"we":[59,92],"propose":[60],"discrete":[62],"diffusion-based":[63],"speech-to-unit":[64],"model":[66,103],"explicit":[68],"duration":[69,135],"control,":[70],"enabling":[71],"time-aligned":[72],"translation.We":[73],"then":[74],"synthesize":[75],"based":[77],"on":[78,116],"translated":[80],"units":[81],"speaker's":[84],"identity":[85],"using":[86],"conditional":[88],"flow":[89],"matching":[90],"model.Additionally,":[91],"introduce":[93],"unit-based":[95],"speed":[96],"adaptation":[97],"mechanism":[98],"guides":[100],"produce":[105],"at":[107],"rate":[109],"consistent":[110],"source,":[113],"without":[114],"relying":[115],"any":[117],"text.Extensive":[118],"experiments":[119],"demonstrate":[120],"our":[122],"framework":[123],"generates":[124],"natural":[125],"fluent":[127],"translations":[128],"align":[130],"original":[133],"speech's":[134],"pace,":[138],"achieving":[140],"competitive":[141],"performance.":[143]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}