{"id":"https://openalex.org/W7126437607","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.46","title":"Prosody in Cascade and Direct Speech-to-Text Translation: a case study on Korean Wh-Phrases","display_name":"Prosody in Cascade and Direct Speech-to-Text Translation: a case study on Korean Wh-Phrases","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126437607","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.46"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.46","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.46","pdf_url":"https://aclanthology.org/2024.findings-eacl.46.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: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.46.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Giulio Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giulio Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tsz Kin Lam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsz Kin Lam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Alexandra Birch","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexandra Birch","raw_affiliation_strings":["School of Informatics , University of Edinburgh , United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics , University of Edinburgh , United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":null,"display_name":"Barry Haddow","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Barry Haddow","raw_affiliation_strings":["School of Informatics , University of Edinburgh , United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics , University of Edinburgh , United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.59594254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"674","last_page":"683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.4341999888420105,"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"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.4341999888420105,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.08179999887943268,"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":0.05270000174641609,"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/prosody","display_name":"Prosody","score":0.6435999870300293},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.5141000151634216},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2786000072956085},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2378000020980835}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6435999870300293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5400999784469604},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.5141000151634216},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47839999198913574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4546999931335449},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41100001335144043},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30489999055862427},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2378000020980835},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2280000001192093}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.46","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.46","pdf_url":"https://aclanthology.org/2024.findings-eacl.46.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: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.46","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.46","pdf_url":"https://aclanthology.org/2024.findings-eacl.46.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: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G373773752","display_name":null,"funder_award_id":"EP/S022481/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314707","display_name":"Government of the United Kingdom","ror":"https://ror.org/05wnh3t63"},{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126437607.pdf","grobid_xml":"https://content.openalex.org/works/W7126437607.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speech-to-Text":[0],"Translation":[1],"(S2TT)":[2],"has":[3,26,50],"typically":[4],"been":[5,27],"addressed":[6],"with":[7,110,138,150],"cascade":[8,135],"systems,":[9],"where":[10,84],"speech":[11,34],"recognition":[12],"systems":[13,36,80,94,133],"generate":[14],"a":[15,22,28,87,96,116,118,121,139,153],"transcription":[16],"that":[17,181],"is":[18,193],"subsequently":[19],"passed":[20],"to":[21,37,52,72,81,107,152,177],"translation":[23,35,65,93,132,136],"model.While":[24],"there":[25],"growing":[29],"interest":[30],"in":[31,47,143,146,156],"developing":[32],"direct":[33,48,78,131,182],"avoid":[38],"propagating":[39],"errors":[40],"and":[41,123,196,201],"losing":[42],"non-verbal":[43],"content,":[44],"prior":[45],"work":[46,67,172],"S2TT":[49,79,183],"struggled":[51],"conclusively":[53],"establish":[54],"the":[55,59,64,75,111,128,162,166,175],"advantages":[56],"of":[57,77,130,161,168],"integrating":[58],"acoustic":[60],"signal":[61],"directly":[62],"into":[63],"process.This":[66],"proposes":[68],"using":[69],"contrastive":[70],"evaluation":[71,192],"quantitatively":[73],"measure":[74],"ability":[76],"disambiguate":[82],"utterances":[83],"prosody":[85],"plays":[86],"crucial":[88],"role.Specifically,":[89],"we":[90],"evaluated":[91],"Korean-English":[92],"on":[95],"test":[97],"set":[98],"containing":[99],"wh-phrases,":[100],"for":[101,159,190,199],"which":[102],"prosodic":[103],"features":[104],"are":[105],"necessary":[106],"produce":[108],"translations":[109],"correct":[112],"intent,":[113],"whether":[114],"it's":[115],"statement,":[117],"yes/no":[119],"question,":[120],"wh-question,":[122],"more.Our":[124],"results":[125],"clearly":[126],"demonstrate":[127],"value":[129],"over":[134],"models,":[137],"notable":[140],"12.9%":[141],"improvement":[142],"overall":[144],"accuracy":[145],"ambiguous":[147],"cases,":[148],"along":[149],"up":[151],"15.6%":[154],"increase":[155],"F1":[157],"scores":[158],"one":[160],"major":[163],"intent":[164],"categories.To":[165],"best":[167],"our":[169,191],"knowledge,":[170],"this":[171],"stands":[173],"as":[174],"first":[176],"provide":[178],"quantitative":[179],"evidence":[180],"models":[184],"can":[185],"effectively":[186],"leverage":[187],"prosody.The":[188],"code":[189],"openly":[194],"accessible":[195],"freely":[197],"available":[198],"review":[200],"utilisation":[202],"1":[203],".":[204]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-15T00:00:00"}