{"id":"https://openalex.org/W4416799019","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249090","title":"Enabling Internationalization of Affective Speech Technology Using LLMs","display_name":"Enabling Internationalization of Affective Speech Technology Using LLMs","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799019","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249090"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249090","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":"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/A5026257400","display_name":"Bo-Hao Su","orcid":"https://orcid.org/0009-0001-0912-7417"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo-Hao Su","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086107623","display_name":"Chi-Chun Lee","orcid":"https://orcid.org/0000-0003-0186-4321"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Chun Lee","raw_affiliation_strings":["Electrical Engineering, National Tsing Hua University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering, National Tsing Hua University,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34626391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2592","last_page":"2597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8349999785423279,"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":0.8349999785423279,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.016699999570846558,"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"}},{"id":"https://openalex.org/T12128","display_name":"AI in Service Interactions","score":0.014299999922513962,"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/affect","display_name":"Affect (linguistics)","score":0.710099995136261},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.4453999996185303},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40369999408721924},{"id":"https://openalex.org/keywords/cultural-diversity","display_name":"Cultural diversity","score":0.4032999873161316},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.37529999017715454},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.3635999858379364}],"concepts":[{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.710099995136261},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4498000144958496},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4438000023365021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40709999203681946},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C125209646","wikidata":"https://www.wikidata.org/wiki/Q1338878","display_name":"Cultural diversity","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3635999858379364},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3614000082015991},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.3068999946117401},{"id":"https://openalex.org/C97509610","wikidata":"https://www.wikidata.org/wiki/Q3141064","display_name":"Internationalization","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249090","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":[{"id":"https://openalex.org/G5724116726","display_name":null,"funder_award_id":"114-2917-I-564-022","funder_id":"https://openalex.org/F2461203286","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F2461203286","display_name":"National Science and Technology Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2128365803","https://openalex.org/W2146334809","https://openalex.org/W2155144982","https://openalex.org/W2742542661","https://openalex.org/W2963686995","https://openalex.org/W3119308075","https://openalex.org/W3137890092","https://openalex.org/W3160183718","https://openalex.org/W3161003523","https://openalex.org/W4205727779","https://openalex.org/W4210528011","https://openalex.org/W4224917001","https://openalex.org/W4225694800","https://openalex.org/W4295308522","https://openalex.org/W4309240333","https://openalex.org/W4313287909","https://openalex.org/W4317514614","https://openalex.org/W4361994820","https://openalex.org/W4372269797","https://openalex.org/W4388767293","https://openalex.org/W4390874791","https://openalex.org/W4391454424","https://openalex.org/W4391718355","https://openalex.org/W4392397287","https://openalex.org/W4392903514","https://openalex.org/W4392903618","https://openalex.org/W4392903739","https://openalex.org/W4392904157","https://openalex.org/W4392904444","https://openalex.org/W4392904630","https://openalex.org/W4392908930","https://openalex.org/W4399267258","https://openalex.org/W4399871910","https://openalex.org/W4400621997","https://openalex.org/W4400975545","https://openalex.org/W4402111363","https://openalex.org/W4402111759","https://openalex.org/W4403258028","https://openalex.org/W4406022688","https://openalex.org/W4408345780","https://openalex.org/W4408352280","https://openalex.org/W4410888432","https://openalex.org/W4415433511","https://openalex.org/W4415798576"],"related_works":[],"abstract_inverted_index":{"Affective":[0],"speech":[1,41,91,184],"technology":[2,185],"aspires":[3],"to":[4,10,72,114,181],"equip":[5],"machines":[6],"with":[7,93],"the":[8,86,102,111,117],"ability":[9],"sense,":[11],"interpret,":[12],"and":[13,23,45,79,101,104,132,166,172,192],"generate":[14],"emotionally":[15],"expressive":[16],"speech,":[17],"enabling":[18],"empathetic":[19],"assistants,":[20],"social":[21],"robots,":[22],"digital":[24],"health":[25],"companions.":[26],"Large":[27],"Audio/Speech":[28],"Language":[29],"Models":[30],"(LALMs/SpeechLMs)":[31],"now":[32],"dominate":[33],"this":[34,138],"space:":[35],"a":[36,142],"single":[37],"model":[38,130],"can":[39],"perform":[40],"recognition,":[42],"affect":[43,63],"detection,":[44],"emotion-controlled":[46],"synthesis,":[47],"achieving":[48],"impressive":[49],"zero-shot":[50],"generalization.":[51],"However,":[52],"we":[53,140,179],"argue":[54],"that":[55,186],"LALMs":[56,160],"are":[57,69],"not":[58],"yet":[59],"internationalized:":[60],"culturally":[61,76,162],"grounded":[62],"is":[64,187,198],"misread":[65],"when":[66],"training":[67],"data":[68,128],"skewed,":[70],"leading":[71,96],"mis-recognition":[73],"of":[74,89,119,149],"affect,":[75,154],"inappropriate":[77],"responses,":[78],"uneven":[80],"user":[81],"experiences.":[82],"This":[83],"paper":[84],"surveys":[85],"current":[87],"state":[88],"affective":[90,183],"processing":[92],"LALMs,":[94],"cataloging":[95],"models,":[97],"their":[98],"sensing-to-synthesis":[99],"capabilities,":[100],"databases":[103],"metrics":[105],"used":[106],"for":[107,158],"evaluation.":[108],"We":[109],"identify":[110],"key":[112],"obstacle":[113],"responsible":[115],"deployment:":[116],"heterogeneity":[118],"human":[120],"vocal":[121,153],"expression":[122],"across":[123],"cultures,":[124],"which":[125],"manifests":[126],"as":[127],"scarcity,":[129],"bias,":[131],"evaluation":[133],"blind":[134],"spots.":[135],"To":[136],"address":[137],"gap,":[139],"propose":[141],"research":[143],"agenda":[144],"comprising:":[145],"(i)":[146],"systematic":[147],"analysis":[148],"cultural":[150],"variation":[151],"in":[152,200],"(ii)":[155],"computational":[156],"strategies":[157],"contextualizing":[159],"toward":[161],"sensitive":[163],"emotion":[164],"processing,":[165],"(iii)":[167],"benchmarks":[168],"featuring":[169],"balanced":[170],"corpora":[171],"culture-aware":[173],"metrics.":[174],"By":[175],"charting":[176],"these":[177],"directions,":[178],"aim":[180],"advance":[182],"globally":[188],"robust,":[189],"socially":[190],"responsible,":[191],"truly":[193],"inclusive.":[194],"The":[195],"overall":[196],"concept":[197],"depicted":[199],"Figure":[201],"1.":[202]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}