{"id":"https://openalex.org/W4408352280","doi":"https://doi.org/10.1109/icassp49660.2025.10889305","title":"Toward Zero-Shot Speech Emotion Recognition Using LLMs in the Absence of Target Data","display_name":"Toward Zero-Shot Speech Emotion Recognition Using LLMs in the Absence of Target Data","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352280","doi":"https://doi.org/10.1109/icassp49660.2025.10889305"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5116594319","display_name":"Su Bo-Hao","orcid":null},"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":"Su Bo-Hao","raw_affiliation_strings":["National Tsing Hua University,Department of Electrical Engineering,Hsinchu,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Electrical Engineering,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073523469","display_name":"Shreya G. Upadhyay","orcid":"https://orcid.org/0009-0000-8411-087X"},"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":"Shreya G. Upadhyay","raw_affiliation_strings":["National Tsing Hua University,Department of Electrical Engineering,Hsinchu,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Electrical Engineering,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103915583","display_name":"Lee Chi\u2010Chun","orcid":null},"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":"Lee Chi-Chun","raw_affiliation_strings":["National Tsing Hua University,Department of Electrical Engineering,Hsinchu,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Electrical Engineering,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":5.019,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94333999,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9876000285148621,"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":0.9876000285148621,"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/T10860","display_name":"Speech and Audio Processing","score":0.9341999888420105,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/shot","display_name":"Shot (pellet)","score":0.6969528198242188},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6859354972839355},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5707530975341797},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5054013729095459},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4902411103248596},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3489178419113159},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.32060086727142334},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22618785500526428},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08897703886032104}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6969528198242188},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6859354972839355},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5707530975341797},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5054013729095459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4902411103248596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3489178419113159},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32060086727142334},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22618785500526428},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08897703886032104},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2102953093","https://openalex.org/W2146334809","https://openalex.org/W2342475039","https://openalex.org/W2742542661","https://openalex.org/W2963686995","https://openalex.org/W3128401974","https://openalex.org/W3197580070","https://openalex.org/W3216260999","https://openalex.org/W4210528011","https://openalex.org/W4225694800","https://openalex.org/W4352990793","https://openalex.org/W4372189490","https://openalex.org/W4382722605","https://openalex.org/W4385822836","https://openalex.org/W4389524085","https://openalex.org/W4391591654","https://openalex.org/W4392903618","https://openalex.org/W4392903739","https://openalex.org/W4392904157","https://openalex.org/W4400770760","https://openalex.org/W4402111512","https://openalex.org/W4403653940","https://openalex.org/W6796464841"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"In":[0,48],"generalized":[1],"Speech":[2],"Emotion":[3],"Recognition":[4],"(SER),":[5],"traditional":[6],"generalization":[7],"techniques":[8],"like":[9],"transfer":[10],"learning":[11],"and":[12,96,116,125,150,176],"domain":[13,24,40],"adaptation":[14],"rely":[15],"on":[16,92,157],"access":[17,56],"to":[18,57,68,87],"some":[19],"amount":[20],"of":[21,77,108,140,170],"unlabeled":[22],"target":[23,39,58,66,89,129],"data.":[25],"However,":[26],"with":[27,82],"increasing":[28],"privacy":[29],"concerns,":[30],"building":[31],"SER":[32,100,111],"systems":[33],"under":[34,101,119],"zero-shot":[35,102,121],"scenarios,":[36],"where":[37],"no":[38],"data":[41,143,147,161,172],"is":[42],"available,":[43],"poses":[44],"a":[45,133],"significant":[46],"challenge.":[47],"such":[49],"cases,":[50],"conventional":[51],"methods":[52],"become":[53],"impractical":[54],"without":[55],"samples":[59],"or":[60],"features.":[61],"To":[62,131],"leverage":[63],"any":[64],"available":[65],"information":[67],"bridge":[69],"this":[70,72],"gap,":[71],"work":[73],"explores":[74],"the":[75,106,138,141,159,168],"potential":[76],"Large":[78],"Language":[79],"Models":[80],"(LLMs),":[81],"their":[83],"powerful":[84],"generative":[85],"capabilities,":[86],"generate":[88],"corpora":[90],"based":[91],"documented":[93],"scenario":[94],"settings":[95],"published":[97],"research,":[98],"enabling":[99],"conditions.":[103],"We":[104],"assess":[105],"effectiveness":[107],"LLMs":[109],"in":[110,173],"tasks":[112],"across":[113],"both":[114,174],"text":[115,175],"speech":[117,177],"modalities":[118],"challenging":[120],"conditions,":[122],"using":[123],"IEMOCAP":[124],"MSP-PODCAST":[126],"as":[127],"unseen":[128],"corpora.":[130],"ensure":[132],"fair":[134],"comparison,":[135],"we":[136],"validate":[137],"performance":[139,169],"synthetic":[142,160],"against":[144],"real":[145,171],"source":[146],"from":[148],"MELD":[149],"MSP-IMPROV.":[151],"Our":[152],"experimental":[153],"results":[154],"reveal":[155],"that,":[156],"average,":[158],"not":[162],"only":[163],"matches":[164],"but":[165],"often":[166],"surpasses":[167],"modalities.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}