{"id":"https://openalex.org/W7130425979","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11384869","title":"Bridging Disfluent to Fluent in Speech Translation: Effective Tagging and Fine-Tuning Strategies","display_name":"Bridging Disfluent to Fluent in Speech Translation: Effective Tagging and Fine-Tuning Strategies","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7130425979","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11384869"},"language":null,"primary_location":{"id":"doi:10.1109/o-cocosda68185.2025.11384869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11384869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5059938986","display_name":"Yuka Ko","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":false,"raw_author_name":"Yuka Ko","raw_affiliation_strings":["Nara Institute of Science and Technology,Nara,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Nara,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051961507","display_name":"Katsuhito Sudoh","orcid":"https://orcid.org/0000-0002-2122-9846"},"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":"Katsuhito Sudoh","raw_affiliation_strings":["Nara Institute of Science and Technology,Nara,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Nara,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"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":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology,Nara,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Nara,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,Nara,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Nara,Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7771999835968018,"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":0.7771999835968018,"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/T12031","display_name":"Speech and dialogue systems","score":0.05999999865889549,"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":0.03629999980330467,"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/bridging","display_name":"Bridging (networking)","score":0.870199978351593},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5805000066757202},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.42149999737739563},{"id":"https://openalex.org/keywords/fluent","display_name":"Fluent","score":0.3912000060081482},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.3709000051021576},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.3544999957084656},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.28780001401901245}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.870199978351593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8036999702453613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6409000158309937},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5805000066757202},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5281000137329102},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.42149999737739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41940000653266907},{"id":"https://openalex.org/C2780411076","wikidata":"https://www.wikidata.org/wiki/Q5462653","display_name":"Fluent","level":3,"score":0.3912000060081482},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.28119999170303345},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2508000135421753},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda68185.2025.11384869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11384869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7839140892028809}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2098152775","https://openalex.org/W2101105183","https://openalex.org/W2899773543","https://openalex.org/W2937176889","https://openalex.org/W2945286432","https://openalex.org/W2963729456","https://openalex.org/W3001434439","https://openalex.org/W3209059054","https://openalex.org/W4285201770","https://openalex.org/W4296068599"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"translation":[1],"(ST)":[2],"converts":[3],"speech":[4,8],"into":[5],"text":[6],"or":[7],"in":[9,16,49,68,105],"the":[10,64],"target":[11],"language.":[12],"A":[13],"major":[14],"challenge":[15],"ST":[17,41,50,78],"is":[18,51],"handling":[19],"spontaneous":[20],"speech,":[21],"which":[22],"often":[23],"includes":[24],"disfluencies":[25,104],"such":[26],"as":[27],"fillers":[28],"and":[29,36,86,96],"hesitations.":[30],"Fluent":[31],"translations":[32],"enhance":[33],"readability,":[34],"clarity,":[35],"usability,":[37],"making":[38],"disfluent-to-fluent":[39],"(D2F)":[40],"highly":[42],"desirable.":[43],"Generally,":[44],"fine-tuning":[45,98],"with":[46,83],"parallel":[47],"data":[48,59,65,82],"effective,":[52],"but":[53],"for":[54,75],"D2F":[55,69],"ST,":[56,70],"limited":[57],"training":[58,73],"constrains":[60],"performance.":[61],"To":[62],"mitigate":[63],"scarcity":[66],"issue":[67],"we":[71],"explore":[72],"strategies":[74],"a":[76],"disfluency-aware":[77],"model,":[79],"utilizing":[80],"augmented":[81],"disfluency":[84,94],"tagging":[85,95],"multi-stage":[87,97],"fine-tuning.":[88],"Our":[89],"experiments":[90],"show":[91],"that":[92],"leveraging":[93],"significantly":[99],"improves":[100],"performance":[101],"while":[102],"reducing":[103],"translation.":[106]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-19T00:00:00"}
