{"id":"https://openalex.org/W4408355306","doi":"https://doi.org/10.1109/icassp49660.2025.10889998","title":"LLM supervised Pre-training for Multimodal Emotion Recognition in Conversations","display_name":"LLM supervised Pre-training for Multimodal Emotion Recognition in Conversations","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355306","doi":"https://doi.org/10.1109/icassp49660.2025.10889998"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889998","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/A5035530630","display_name":"Soumya Dutta","orcid":"https://orcid.org/0000-0002-3936-6718"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soumya Dutta","raw_affiliation_strings":["Electrical Engineering Indian Institute of Science Bangalore,LEAP Lab,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering Indian Institute of Science Bangalore,LEAP Lab,Bangalore,India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":["Electrical Engineering Indian Institute of Science Bangalore,LEAP Lab,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering Indian Institute of Science Bangalore,LEAP Lab,Bangalore,India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":42.6328,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.99872814,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9988999962806702,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9915000200271606,"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/computer-science","display_name":"Computer science","score":0.7267131805419922},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6092501282691956},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5960010290145874},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48379725217819214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4287315607070923},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3587612509727478}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267131805419922},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6092501282691956},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5960010290145874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48379725217819214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4287315607070923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3587612509727478},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889998","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W38739846","https://openalex.org/W1002150248","https://openalex.org/W1578859036","https://openalex.org/W2028975938","https://openalex.org/W2084046180","https://openalex.org/W2092615387","https://openalex.org/W2144012961","https://openalex.org/W2146334809","https://openalex.org/W2398936787","https://openalex.org/W2465534249","https://openalex.org/W2584561145","https://openalex.org/W2624419954","https://openalex.org/W2740550900","https://openalex.org/W2742542661","https://openalex.org/W2774090594","https://openalex.org/W2889191349","https://openalex.org/W2892370324","https://openalex.org/W2896457183","https://openalex.org/W2913894054","https://openalex.org/W2930957955","https://openalex.org/W2936162287","https://openalex.org/W2945662934","https://openalex.org/W2958722525","https://openalex.org/W2963686995","https://openalex.org/W2963873807","https://openalex.org/W2965373594","https://openalex.org/W2966715458","https://openalex.org/W2985882473","https://openalex.org/W2997258743","https://openalex.org/W3015213852","https://openalex.org/W3021080764","https://openalex.org/W3036601975","https://openalex.org/W3103291722","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211488063","https://openalex.org/W4206326349","https://openalex.org/W4221147459","https://openalex.org/W4224916926","https://openalex.org/W4225266919","https://openalex.org/W4288089799","https://openalex.org/W4321524280","https://openalex.org/W4366197508","https://openalex.org/W4367694159","https://openalex.org/W4385570970","https://openalex.org/W4385573848","https://openalex.org/W4385822632","https://openalex.org/W4387891768","https://openalex.org/W4389519239","https://openalex.org/W4401042286","https://openalex.org/W4401043060","https://openalex.org/W4401043218","https://openalex.org/W4403618430","https://openalex.org/W4404781855","https://openalex.org/W4412285165","https://openalex.org/W6605703937","https://openalex.org/W6638733343","https://openalex.org/W6719667659","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6758674704","https://openalex.org/W6766673545","https://openalex.org/W6766904570","https://openalex.org/W6769318315","https://openalex.org/W6769627184","https://openalex.org/W6780218876","https://openalex.org/W6847363464","https://openalex.org/W6850724024","https://openalex.org/W6851555575","https://openalex.org/W6852497449","https://openalex.org/W6857054612","https://openalex.org/W6873746420"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W4412817058","https://openalex.org/W3216976533","https://openalex.org/W3204019825","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Emotion":[0],"recognition":[1,25,74,85],"in":[2,86,110],"conversations":[3,87],"(ERC)":[4],"is":[5,52,107],"challenging":[6],"due":[7],"to":[8,21,54],"the":[9,13,78,104,112,116,135],"multimodal":[10],"nature":[11,114],"of":[12,102,115,149],"emotion":[14,73,84],"expression.":[15],"In":[16],"this":[17],"paper,":[18],"we":[19,132],"propose":[20],"pretrain":[22],"a":[23,39,44,94],"text-based":[24,72],"model":[26,51,106,137],"from":[27,38,93],"unsupervised":[28],"speech":[29,41,90],"transcripts":[30,63],"with":[31,43,89],"LLM":[32,50],"guidance.":[33],"These":[34],"transcriptions":[35],"are":[36,64],"obtained":[37,92],"raw":[40],"dataset":[42],"pre-trained":[45,97],"ASR":[46],"system.":[47],"A":[48,99],"text":[49,81],"queried":[53],"provide":[55],"pseudo-labels":[56],"for":[57,67,83],"these":[58,61,150],"transcripts,":[59],"and":[60,128,142],"pseudo-labeled":[62],"subsequently":[65],"used":[66],"learning":[68],"an":[69],"utterance":[70,79],"level":[71,80],"model.":[75,98],"We":[76,118],"use":[77],"embeddings":[82,91],"along":[88],"recently":[95],"proposed":[96,136],"hierarchical":[100],"way":[101],"training":[103],"speech-text":[105],"proposed,":[108],"keeping":[109],"mind":[111],"conversational":[113],"dataset.":[117],"perform":[119],"experiments":[120],"on":[121,146],"three":[122,151],"established":[123],"datasets,":[124],"namely,":[125],"IEMOCAP,":[126],"MELD,":[127],"CMU-":[129],"MOSI,":[130],"where":[131],"illustrate":[133],"that":[134],"improves":[138],"over":[139],"other":[140],"benchmarks":[141],"achieves":[143],"state-of-the-art":[144],"results":[145],"two":[147],"out":[148],"datasets.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":8}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}