{"id":"https://openalex.org/W4392903739","doi":"https://doi.org/10.1109/icassp48485.2024.10448316","title":"Large Language Model-Based Emotional Speech Annotation Using Context and Acoustic Feature for Speech Emotion Recognition","display_name":"Large Language Model-Based Emotional Speech Annotation Using Context and Acoustic Feature for Speech Emotion Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903739","doi":"https://doi.org/10.1109/icassp48485.2024.10448316"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5002430203","display_name":"Jennifer Santoso","orcid":"https://orcid.org/0000-0001-7723-3396"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jennifer Santoso","raw_affiliation_strings":["RevComm, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RevComm, Inc","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009504718","display_name":"Kenkichi Ishizuka","orcid":null},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kenkichi Ishizuka","raw_affiliation_strings":["RevComm, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RevComm, Inc","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004638586","display_name":"Taiichi Hashimoto","orcid":"https://orcid.org/0000-0002-6588-9790"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Taiichi Hashimoto","raw_affiliation_strings":["RevComm, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RevComm, Inc","institution_ids":["https://openalex.org/I19268510"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I19268510"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11026","last_page":"11030"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.8697166442871094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7841994762420654},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6352818608283997},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5752587914466858},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5568314790725708},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5468931794166565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.512677788734436},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4999735355377197},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.455719918012619},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4537135362625122},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14642852544784546}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8697166442871094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7841994762420654},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6352818608283997},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5752587914466858},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5568314790725708},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5468931794166565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.512677788734436},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4999735355377197},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.455719918012619},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4537135362625122},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14642852544784546},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":26,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2191779130","https://openalex.org/W2583743457","https://openalex.org/W2896457183","https://openalex.org/W2963873807","https://openalex.org/W2963980299","https://openalex.org/W3015427680","https://openalex.org/W3096723250","https://openalex.org/W3163091219","https://openalex.org/W3176770275","https://openalex.org/W3197947674","https://openalex.org/W3199958362","https://openalex.org/W4221162872","https://openalex.org/W4225635674","https://openalex.org/W4283016277","https://openalex.org/W4292779060","https://openalex.org/W4309201339","https://openalex.org/W4327811957","https://openalex.org/W4366733439","https://openalex.org/W4372266212","https://openalex.org/W4375928984","https://openalex.org/W4385822715","https://openalex.org/W4385822805","https://openalex.org/W4385822836","https://openalex.org/W4385823029","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W1968552888","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W1511346092","https://openalex.org/W1527532029","https://openalex.org/W2378167147","https://openalex.org/W3210777354","https://openalex.org/W2281307425","https://openalex.org/W2772323916"],"abstract_inverted_index":{"The":[0,125],"remarkable":[1],"emergence":[2],"of":[3,29,35,40,55,72,92],"large":[4],"language":[5],"models":[6],"(LLM)":[7],"and":[8,32,76,100],"their":[9],"vast":[10],"capabilities":[11],"have":[12],"opened":[13],"a":[14,48,133,141],"possibility":[15],"for":[16],"applications":[17],"in":[18],"various":[19],"fields,":[20],"including":[21],"speech":[22,36,42,112],"emotion":[23],"recognition":[24],"(SER).":[25],"Despite":[26],"the":[27,33,38,53,70,78,84,90,106,129],"advancement":[28],"SER":[30,126,146],"methods":[31],"abundance":[34],"data,":[37],"requirement":[39],"having":[41],"data":[43,136,139],"labeled":[44],"with":[45,120],"emotions":[46],"is":[47],"challenge":[49],"to":[50,65,144],"fulfill,":[51],"considering":[52],"cost":[54],"human":[56,118],"annotation.":[57],"In":[58],"this":[59],"study,":[60],"we":[61,87],"propose":[62],"utilizing":[63],"LLM":[64],"annotate":[66],"emotional":[67,96,111],"speeches,":[68],"investigating":[69],"use":[71],"conversation":[73],"sequence":[74],"transcription,":[75],"incorporating":[77],"textual":[79],"acoustic":[80],"feature":[81],"descriptors":[82],"into":[83],"prompt.":[85],"Furthermore,":[86],"also":[88],"examine":[89],"application":[91],"annotation":[93,113,119,123,130],"results":[94],"on":[95],"speeches":[97],"as":[98,132],"training":[99,135],"augmentation":[101,138],"data.":[102],"Our":[103],"experiment":[104],"using":[105,114,128],"IEMOCAP":[107],"dataset":[108],"shows":[109],"that":[110],"LLMs":[115],"can":[116],"outperform":[117],"possibly":[121],"lower":[122],"costs.":[124],"trained":[127],"result":[131],"whole":[134],"or":[137],"reaches":[140],"performance":[142],"close":[143],"state-of-the-art":[145],"methods.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}