{"id":"https://openalex.org/W7130389431","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385054","title":"Measuring Emotion Preservation in Expressive Speech-to-Speech Translation","display_name":"Measuring Emotion Preservation in Expressive Speech-to-Speech Translation","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7130389431","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385054"},"language":null,"primary_location":{"id":"doi:10.1109/o-cocosda68185.2025.11385054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385054","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/A5065879041","display_name":"Bagus Tris Atmaja","orcid":"https://orcid.org/0000-0003-1560-2824"},"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":"Bagus Tris Atmaja","raw_affiliation_strings":["Nara Institute of Science and Technology,Ikoma,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Ikoma,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126304777","display_name":"Toru Shirai","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":"Toru Shirai","raw_affiliation_strings":["Nara Institute of Science and Technology,Ikoma,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Ikoma,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,Ikoma,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Ikoma,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/T10667","display_name":"Emotion and Mood Recognition","score":0.9897000193595886,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9897000193595886,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.002400000113993883,"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/T12488","display_name":"Mental Health via Writing","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6963000297546387},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6384000182151794},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6308000087738037},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.4991999864578247},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.47870001196861267},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4632999897003174}],"concepts":[{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6963000297546387},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6384000182151794},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6308000087738037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5194000005722046},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.4991999864578247},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.47870001196861267},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45719999074935913},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42890000343322754},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.42250001430511475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.398499995470047},{"id":"https://openalex.org/C2776141551","wikidata":"https://www.wikidata.org/wiki/Q16000087","display_name":"Emotion perception","level":3,"score":0.367900013923645},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.33399999141693115},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C117409633","wikidata":"https://www.wikidata.org/wiki/Q5373756","display_name":"Emotion work","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C2778143943","wikidata":"https://www.wikidata.org/wiki/Q523747","display_name":"Expressed emotion","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda68185.2025.11385054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385054","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2053154970","https://openalex.org/W2963686995","https://openalex.org/W3120680448","https://openalex.org/W3140429000","https://openalex.org/W3197912431","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4287854499","https://openalex.org/W4361994820","https://openalex.org/W4385570550","https://openalex.org/W4402669711","https://openalex.org/W4402684068","https://openalex.org/W4405633023","https://openalex.org/W4406461501","https://openalex.org/W4408258400"],"related_works":[],"abstract_inverted_index":{"Measuring":[0],"how":[1],"well":[2],"emotions":[3],"are":[4],"preserved":[5,75],"in":[6,76,80],"speech-to-speech":[7,140],"translation":[8,78],"is":[9,74],"a":[10],"difficult":[11],"task.":[12],"Previous":[13],"research":[14],"focused":[15],"on":[16],"measuring":[17],"the":[18,33,71,77,81,119,133],"similarity":[19],"between":[20,109],"speech":[21,50],"embeddings":[22,111,122],"related":[23],"to":[24,127],"emotion":[25,44,51,58,73,101,110,116],"or":[26],"prosody,":[27],"which":[28],"may":[29],"not":[30,113],"accurately":[31],"capture":[32],"emotional":[34,137],"contents.":[35],"This":[36],"study":[37],"proposes":[38],"more":[39],"direct":[40],"approaches":[41],"by":[42],"evaluating":[43],"preservation":[45,59],"using":[46],"metrics":[47,85],"derived":[48],"from":[49],"recognition":[52],"(SER),":[53],"including":[54],"balanced":[55,88],"accuracy":[56,89],"ratio,":[57,90],"rate,":[60],"and":[61,93],"Cohen's":[62],"Kappa.":[63],"The":[64,130],"results":[65],"show":[66],"that":[67,106],"about":[68],"half":[69],"of":[70,100,135],"original":[72],"process":[79],"MELD-ST":[82],"dataset,":[83],"with":[84],"such":[86],"as":[87,97],"valence-arousal":[91],"similarity,":[92],"pause":[94],"rate":[95],"serving":[96],"reliable":[98],"indicators":[99],"preservation.":[102],"We":[103],"also":[104],"found":[105],"high":[107],"similarities":[108],"do":[112],"necessarily":[114],"mean":[115],"preservation,":[117],"since":[118],"same":[120],"acoustic":[121],"used":[123],"for":[124],"SER":[125],"lead":[126],"distinct":[128],"performance.":[129],"analysis":[131],"highlights":[132],"challenges":[134],"maintaining":[136],"consistency":[138],"during":[139],"translation.":[141]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-19T00:00:00"}