{"id":"https://openalex.org/W4415709309","doi":"https://doi.org/10.1109/icme59968.2025.11209040","title":"Large Language Models Meet Contrastive Learning: Zero-Shot Emotion Recognition Across Languages","display_name":"Large Language Models Meet Contrastive Learning: Zero-Shot Emotion Recognition Across Languages","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709309","doi":"https://doi.org/10.1109/icme59968.2025.11209040"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","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/A5023152132","display_name":"Heqing Zou","orcid":"https://orcid.org/0000-0003-0038-2822"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Heqing Zou","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009594218","display_name":"Fengmao Lv","orcid":"https://orcid.org/0000-0003-1640-0992"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengmao Lv","raw_affiliation_strings":["Southwest Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110794889","display_name":"Desheng Zheng","orcid":"https://orcid.org/0000-0002-0994-4660"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Desheng Zheng","raw_affiliation_strings":["Kash Institute of Electronics and Information Industry"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kash Institute of Electronics and Information Industry","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009372982","display_name":"Deepu Rajan","orcid":"https://orcid.org/0000-0001-7788-8368"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Deepu Rajan","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4863,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94775697,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"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":0.9919000267982483,"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":0.9919000267982483,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.001500000013038516,"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":0.00139999995008111,"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/emotion-recognition","display_name":"Emotion recognition","score":0.5388000011444092},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.36419999599456787},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3504999876022339},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34040001034736633},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.311599999666214},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.3073999881744385},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.2987000048160553},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.27970001101493835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.678600013256073},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5388000011444092},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4977000057697296},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4975000023841858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3797999918460846},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.36419999599456787},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.31200000643730164},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.311599999666214},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C2781202465","wikidata":"https://www.wikidata.org/wiki/Q18346297","display_name":"Lexical diversity","level":3,"score":0.26980000734329224},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2061068689","https://openalex.org/W2146334809","https://openalex.org/W2742542661","https://openalex.org/W2808331624","https://openalex.org/W2883409523","https://openalex.org/W2896596895","https://openalex.org/W2963686995","https://openalex.org/W3041794018","https://openalex.org/W3081192838","https://openalex.org/W3095319910","https://openalex.org/W3099284785","https://openalex.org/W3120709499","https://openalex.org/W3197912431","https://openalex.org/W3207924272","https://openalex.org/W4221162872","https://openalex.org/W4224918181","https://openalex.org/W4296930501","https://openalex.org/W4313887688","https://openalex.org/W4382722605","https://openalex.org/W4385571742","https://openalex.org/W4391021646","https://openalex.org/W4392172995","https://openalex.org/W4392903618","https://openalex.org/W4392903739","https://openalex.org/W4392904345","https://openalex.org/W4392904649","https://openalex.org/W4393147046","https://openalex.org/W4401827145","https://openalex.org/W4402111512","https://openalex.org/W4402115910","https://openalex.org/W4402669711"],"related_works":[],"abstract_inverted_index":{"Multilingual":[0],"speech":[1,31,49,59,72,86,100,115,121],"emotion":[2,32,60,101,116,122],"recognition":[3,117],"aims":[4],"to":[5,46,70],"estimate":[6],"a":[7,12,65,96],"speaker\u2019s":[8],"emotional":[9,79],"state":[10],"using":[11],"contactless":[13],"method":[14,112],"across":[15],"different":[16],"languages.":[17,129],"However,":[18],"variability":[19],"in":[20,77,91,113],"voice":[21],"characteristics":[22],"and":[23,51,84,118,128,133],"linguistic":[24,75],"diversity":[25],"poses":[26],"significant":[27],"challenges":[28],"for":[29,56],"zero-shot":[30,57,119],"recognition,":[33,123],"especially":[34],"with":[35,74],"multilingual":[36,48,58,99,120],"datasets.":[37],"In":[38],"this":[39,92],"paper,":[40],"we":[41,63,94],"propose":[42],"leveraging":[43],"contrastive":[44],"learning":[45],"refine":[47],"features":[50,76],"extend":[52],"large":[53],"language":[54],"models":[55],"estimation.":[61],"Specifically,":[62],"employ":[64],"novel":[66],"two-stage":[67],"training":[68],"framework":[69],"align":[71],"signals":[73],"the":[78,107,110],"space,":[80],"capturing":[81],"both":[82,114],"emotion-aware":[83],"language-agnostic":[85],"representations.":[87],"To":[88],"advance":[89],"research":[90],"field,":[93],"introduce":[95],"large-scale":[97],"synthetic":[98],"dataset,":[102],"M5SER.":[103],"Our":[104,130],"experiments":[105],"demonstrate":[106],"effectiveness":[108],"of":[109],"proposed":[111],"including":[124],"previously":[125],"unseen":[126],"datasets":[127],"introduced":[131],"dataset":[132],"related":[134],"code":[135],"will":[136],"be":[137],"available":[138],"on":[139],"GitHub<sup":[140],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[141],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-30T00:00:00"}