{"id":"https://openalex.org/W7164738098","doi":"https://doi.org/10.5715/jnlp.33.452","title":"Emotion-aware Speech Translation Correction with Large Language Models","display_name":"Emotion-aware Speech Translation Correction with Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7164738098","doi":"https://doi.org/10.5715/jnlp.33.452"},"language":"en","primary_location":{"id":"doi:10.5715/jnlp.33.452","is_oa":true,"landing_page_url":"https://doi.org/10.5715/jnlp.33.452","pdf_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_452/_pdf","source":{"id":"https://openalex.org/S4210212357","display_name":"Journal of Natural Language Processing","issn_l":"1340-7619","issn":["1340-7619","2185-8314"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Natural Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_452/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109209901","display_name":"Zhengdong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhengdong Yang","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["School of Engineering, Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102757632","display_name":"Chenhui Chu","orcid":"https://orcid.org/0000-0001-9848-6384"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chenhui Chu","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.61738109,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"2","first_page":"452","last_page":"472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.29919999837875366,"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":0.29919999837875366,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.17190000414848328,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.07339999824762344,"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":0.4643000066280365},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.36640000343322754},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.361299991607666},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.3531999886035919},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3034999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6797000169754028},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5361999869346619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5022000074386597},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46639999747276306},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4643000066280365},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.3531999886035919},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33009999990463257},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2671999931335449}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5715/jnlp.33.452","is_oa":true,"landing_page_url":"https://doi.org/10.5715/jnlp.33.452","pdf_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_452/_pdf","source":{"id":"https://openalex.org/S4210212357","display_name":"Journal of Natural Language Processing","issn_l":"1340-7619","issn":["1340-7619","2185-8314"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Natural Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.5715/jnlp.33.452","is_oa":true,"landing_page_url":"https://doi.org/10.5715/jnlp.33.452","pdf_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_452/_pdf","source":{"id":"https://openalex.org/S4210212357","display_name":"Journal of Natural Language Processing","issn_l":"1340-7619","issn":["1340-7619","2185-8314"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Natural Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7164738098.pdf","grobid_xml":"https://content.openalex.org/works/W7164738098.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,104],"study":[1],"emotion-aware":[2],"speech-to-text":[3],"translation":[4,23,38],"(ST)":[5],"through":[6],"the":[7,22,29,37,41,48,54,60,64,80,85,95,100,108,123,126],"lens":[8],"of":[9,24,125,128],"generative":[10],"error":[11],"correction":[12],"(GER)":[13],"with":[14,87,99,112],"large":[15],"language":[16],"models":[17],"(LLMs).":[18],"First,":[19],"we":[20,46,68],"enhance":[21],"emotional":[25],"speech":[26],"by":[27],"adopting":[28],"GER":[30,81,118,129],"paradigm:":[31],"Finetune":[32],"an":[33],"LLM":[34,55],"to":[35,58,62],"generate":[36,94],"based":[39],"on":[40,107],"decoded":[42],"N-best":[43,114],"hypotheses.":[44],"Next,":[45],"combine":[47],"emotion":[49,65,86,138],"and":[50,92,117,130,133],"sentiment":[51],"labels":[52],"into":[53],"finetuning":[56],"process":[57],"enable":[59],"model":[61,82],"consider":[63],"content.":[66],"Moreover,":[67],"introduce":[69],"Describe-then-Translate":[70],"(DtT),":[71],"a":[72,88],"simple":[73],"yet":[74],"effective":[75],"rationale-style":[76],"supervision":[77],"that":[78],"makes":[79],"first":[83],"predict":[84],"brief":[89],"natural-language":[90],"sentence":[91],"then":[93],"translation,":[96],"which":[97],"aligns":[98],"LLM\u2019s":[101],"language-modeling":[102],"objective.":[103],"conducted":[105],"experiments":[106],"English-Chinese":[109],"BMELD":[110],"dataset":[111],"different":[113],"generation":[115],"strategies":[116],"models.":[119],"The":[120],"results":[121],"show":[122],"effectiveness":[124],"combination":[127],"emotion/sentiment":[131],"labels,":[132],"DtT":[134],"improves":[135],"over":[136],"label-only":[137],"supervision.":[139]},"counts_by_year":[],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2026-06-15T00:00:00"}