{"id":"https://openalex.org/W4408354408","doi":"https://doi.org/10.1109/icassp49660.2025.10888591","title":"Revise, Reason, and Recognize: LLM-Based Emotion Recognition via Emotion-Specific Prompts and ASR Error Correction","display_name":"Revise, Reason, and Recognize: LLM-Based Emotion Recognition via Emotion-Specific Prompts and ASR Error Correction","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354408","doi":"https://doi.org/10.1109/icassp49660.2025.10888591"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888591","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/20.500.11820/228e694c-77fb-4e5e-9b6d-c7cf0d939aff","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102935391","display_name":"Yuanchao Li","orcid":"https://orcid.org/0000-0002-9490-8209"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yuanchao Li","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101858855","display_name":"Yuan Gong","orcid":"https://orcid.org/0009-0009-9097-4805"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Gong","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chao-Han Huck Yang","raw_affiliation_strings":["NVIDIA Research"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081337679","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0003-4415-7408"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058881584","display_name":"Catherine Lai","orcid":"https://orcid.org/0000-0003-2411-8954"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Catherine Lai","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102935391"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":14.4806,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98864517,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"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":0.8474000096321106,"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":0.8474000096321106,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7365999817848206,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.7312999963760376,"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":0.7201697826385498},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.7177095413208008},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6219829320907593},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.4861604869365692},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.42452242970466614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4037209153175354},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36075711250305176},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.34023040533065796},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3206305503845215},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.28494778275489807},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13148769736289978}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7201697826385498},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7177095413208008},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6219829320907593},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.4861604869365692},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.42452242970466614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4037209153175354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36075711250305176},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.34023040533065796},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3206305503845215},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.28494778275489807},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13148769736289978}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888591","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"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/228e694c-77fb-4e5e-9b6d-c7cf0d939aff","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/228e694c-77fb-4e5e-9b6d-c7cf0d939aff","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Li, Y, Gong, Y, Yang, C-H H, Bell, P & Lai, C 2025, Revise, reason, and recognize : LLM-based emotion recognition via emotion-specific prompts and ASR error correction. in Proceedings of the 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Institute of Electrical and Electronics Engineers, Piscataway, NJ, USA, pp. 1-6, 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, Hyderabad, India, 6/04/25. https://doi.org/10.1109/ICASSP49660.2025.10888591","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/228e694c-77fb-4e5e-9b6d-c7cf0d939aff","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/228e694c-77fb-4e5e-9b6d-c7cf0d939aff","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Li, Y, Gong, Y, Yang, C-H H, Bell, P & Lai, C 2025, Revise, reason, and recognize : LLM-based emotion recognition via emotion-specific prompts and ASR error correction. in Proceedings of the 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Institute of Electrical and Electronics Engineers, Piscataway, NJ, USA, pp. 1-6, 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, Hyderabad, India, 6/04/25. https://doi.org/10.1109/ICASSP49660.2025.10888591","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/228e694c-77fb-4e5e-9b6d-c7cf0d939aff","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/228e694c-77fb-4e5e-9b6d-c7cf0d939aff","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Li, Y, Gong, Y, Yang, C-H H, Bell, P & Lai, C 2025, Revise, reason, and recognize : LLM-based emotion recognition via emotion-specific prompts and ASR error correction. in Proceedings of the 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Institute of Electrical and Electronics Engineers, Piscataway, NJ, USA, pp. 1-6, 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, Hyderabad, India, 6/04/25. https://doi.org/10.1109/ICASSP49660.2025.10888591","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2742542661","https://openalex.org/W2970062726","https://openalex.org/W2972602947","https://openalex.org/W4385822632","https://openalex.org/W4385822836","https://openalex.org/W4388708748","https://openalex.org/W4389520366","https://openalex.org/W4391021773","https://openalex.org/W4392903618","https://openalex.org/W4392903739","https://openalex.org/W4399154371","https://openalex.org/W4399267112","https://openalex.org/W4401023650","https://openalex.org/W4401042738","https://openalex.org/W4406461641","https://openalex.org/W4406461710","https://openalex.org/W4406524040","https://openalex.org/W4409763349","https://openalex.org/W6796581206","https://openalex.org/W6857660365"],"related_works":["https://openalex.org/W3126677997","https://openalex.org/W1610857240","https://openalex.org/W1550318927","https://openalex.org/W4305042383","https://openalex.org/W2773396412","https://openalex.org/W4380854332","https://openalex.org/W2184859701","https://openalex.org/W4386232293","https://openalex.org/W2546649374","https://openalex.org/W4380370144"],"abstract_inverted_index":{"Annotating":[0],"and":[1,22,51,97,136,156],"recognizing":[2],"speech":[3],"emotion":[4,82,142,154],"using":[5],"prompt":[6,122],"engineering":[7],"has":[8],"recently":[9],"emerged":[10],"with":[11,38,69,87],"the":[12,39,56,104,116,127,130,149],"advancement":[13],"of":[14,41,58,106,118,129,151],"Large":[15],"Language":[16],"Models":[17],"(LLMs),":[18],"yet":[19],"its":[20],"efficacy":[21,128],"reliability":[23],"remain":[24],"questionable.":[25],"In":[26],"this":[27,35,111],"paper,":[28],"we":[29,54,73,114],"conduct":[30],"a":[31,75],"systematic":[32],"study":[33,145],"on":[34,61,92],"topic,":[36],"beginning":[37],"proposal":[40],"novel":[42],"prompts":[43],"that":[44],"incorporate":[45],"emotion-specific":[46,131],"knowledge":[47],"from":[48,84],"acoustics,":[49],"linguistics,":[50],"psychology.":[52],"Subsequently,":[53],"examine":[55,103],"effectiveness":[57],"LLM-based":[59,81,141],"prompting":[60,77],"Automatic":[62],"Speech":[63],"Recognition":[64],"(ASR)":[65],"transcription,":[66],"contrasting":[67],"it":[68],"ground-truth":[70],"transcription.":[71],"Furthermore,":[72],"propose":[74],"Revise-Reason-Recognize":[76],"pipeline":[78],"for":[79,140],"robust":[80],"recognition":[83,155],"spoken":[85],"language":[86],"ASR":[88,133],"errors.":[89],"Additionally,":[90],"experiments":[91],"context-aware":[93],"learning,":[94,96],"in-context":[95],"instruction":[98],"tuning":[99],"are":[100],"performed":[101],"to":[102,120,147],"usefulness":[105],"LLM":[107,137],"training":[108,138],"schemes":[109,139],"in":[110,153],"direction.":[112],"Finally,":[113],"investigate":[115],"sensitivity":[117],"LLMs":[119,152],"minor":[121],"variations.":[123],"Experimental":[124],"results":[125],"demonstrate":[126],"prompts,":[132],"error":[134],"correction,":[135],"recognition.":[143],"Our":[144],"aims":[146],"refine":[148],"use":[150],"related":[157],"domains.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}