{"id":"https://openalex.org/W4416798454","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249323","title":"Beyond One-Shot Dubbing: Leveraging N-Best Translation and Prompted Paraphrasing with Synchrony-Aware Re-Ranking","display_name":"Beyond One-Shot Dubbing: Leveraging N-Best Translation and Prompted Paraphrasing with Synchrony-Aware Re-Ranking","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798454","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249323"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249323","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/A5114359747","display_name":"Jan Meyer Saragih","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jan Meyer Saragih","raw_affiliation_strings":["Nara Institute of Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083937952","display_name":"Faisal Mehmood","orcid":"https://orcid.org/0000-0003-4420-0517"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Faisal Mehmood","raw_affiliation_strings":["Nara Institute of Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114359747"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40611706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1146","last_page":"1151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2808000147342682,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2808000147342682,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.14560000598430634,"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":0.09910000115633011,"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/translation","display_name":"Translation (biology)","score":0.5837000012397766},{"id":"https://openalex.org/keywords/synchronizing","display_name":"Synchronizing","score":0.5813000202178955},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5788000226020813},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5713000297546387},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.53329998254776},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4691999852657318},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.45989999175071716},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832000255584717},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5837000012397766},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.5813000202178955},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5788000226020813},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5758000016212463},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5713000297546387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5562999844551086},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.53329998254776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4975000023841858},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4375},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249323","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":16,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2119168550","https://openalex.org/W3084396630","https://openalex.org/W3103450644","https://openalex.org/W4319862635","https://openalex.org/W4382202818","https://openalex.org/W4382357812","https://openalex.org/W4385571488","https://openalex.org/W4385822664","https://openalex.org/W4389519402","https://openalex.org/W4402227281","https://openalex.org/W4402669744","https://openalex.org/W4402669762","https://openalex.org/W4402683080","https://openalex.org/W4411119594","https://openalex.org/W4411120238"],"related_works":[],"abstract_inverted_index":{"Dubbing\u2014translating":[0],"and":[1,18,44,54,71,87,124,133,150,165,179],"synchronizing":[2],"spoken":[3],"content":[4],"across":[5],"languages\u2014requires":[6],"not":[7],"only":[8],"semantic":[9],"accuracy":[10],"but":[11],"also":[12],"precise":[13],"alignment":[14,97,119,129],"with":[15,30,74],"the":[16,21,50,101,109,131,147,151,171],"timing":[17],"rhythm":[19],"of":[20,52,96,173],"original":[22],"speech.":[23],"While":[24],"recent":[25],"work":[26],"has":[27],"explored":[28],"paraphrasing":[29,47,73],"large":[31],"language":[32],"models":[33],"(LLMs)":[34],"for":[35,182],"dubbing,":[36],"most":[37],"approaches":[38],"rely":[39],"on":[40,117,143],"a":[41,45,62],"single":[42],"translation":[43,69,175],"one-shot":[46],"pass,":[48],"limiting":[49],"space":[51,92],"alternatives":[53],"often":[55],"resulting":[56],"in":[57,85],"suboptimal":[58],"alignment.":[59],"We":[60],"propose":[61],"multi-candidate":[63],"framework":[64],"that":[65,80,159],"leverages":[66],"N-best":[67],"machine":[68],"outputs":[70],"in-context":[72],"LLMs":[75],"to":[76],"generate":[77],"diverse":[78],"candidates":[79],"preserve":[81],"meaning":[82],"while":[83],"varying":[84],"structure":[86],"length.":[88],"This":[89],"expanded":[90],"candidate":[91],"enables":[93],"better":[94],"exploration":[95],"options":[98],"without":[99,136],"modifying":[100],"underlying":[102],"MT":[103],"or":[104,140],"TTS":[105],"systems.":[106],"To":[107],"select":[108],"best":[110],"output,":[111],"we":[112],"introduce":[113],"synchrony-aware":[114],"reranking":[115],"based":[116],"speech-only":[118],"metrics\u2014specifically":[120],"Speech":[121,125],"Length":[122],"Compliance":[123],"Overlap\u2014which":[126],"quantify":[127],"temporal":[128,163],"between":[130],"generated":[132],"reference":[134],"speech":[135],"requiring":[137],"video":[138],"input":[139],"retraining.":[141],"Experiments":[142],"German-to-English":[144],"dubbing":[145],"using":[146],"FLEURS":[148],"dataset":[149],"IWSLT":[152],"2024":[153],"Dubbing":[154],"Challenge":[155],"test":[156],"set":[157],"show":[158],"our":[160],"approach":[161],"improves":[162],"synchrony":[164],"perceived":[166],"naturalness.":[167],"These":[168],"results":[169],"highlight":[170],"value":[172],"combining":[174],"diversity,":[176],"incontext":[177],"paraphrasing,":[178],"synchrony-based":[180],"selection":[181],"highquality":[183],"automatic":[184],"dubbing.":[185]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}