{"id":"https://openalex.org/W7148234699","doi":"https://doi.org/10.1109/asru65441.2025.11434728","title":"Few-shot Personalization via In-Context Learning for Speech Emotion Recognition based on Speech-Language Model","display_name":"Few-shot Personalization via In-Context Learning for Speech Emotion Recognition based on Speech-Language Model","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148234699","doi":"https://doi.org/10.1109/asru65441.2025.11434728"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5027118468","display_name":"Mana Ihori","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Mana Ihori","raw_affiliation_strings":["NTT, Inc.,Human Informatics Laboratories,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc.,Human Informatics Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102511251","display_name":"Taiga Yamane","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taiga Yamane","raw_affiliation_strings":["NTT, Inc.,Human Informatics Laboratories,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc.,Human Informatics Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016817412","display_name":"Naotaka Kawata","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naotaka Kawata","raw_affiliation_strings":["NTT, Inc.,Human Informatics Laboratories,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc.,Human Informatics Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082466886","display_name":"Naoki Makishima","orcid":"https://orcid.org/0000-0002-7065-315X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoki Makishima","raw_affiliation_strings":["NTT, Inc.,Human Informatics Laboratories,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc.,Human Informatics Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132817362","display_name":"Tomohiro Tanaka","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":["NTT, Inc.,Human Informatics Laboratories,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc.,Human Informatics Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132826971","display_name":"Satoshi Suzuki","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Suzuki","raw_affiliation_strings":["NTT, Inc.,Human Informatics Laboratories,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc.,Human Informatics Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013009514","display_name":"Shota Orihashi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Orihashi","raw_affiliation_strings":["NTT, Inc.,Human Informatics Laboratories,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc.,Human Informatics Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT, Inc.,Human Informatics Laboratories,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc.,Human Informatics Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5027118468"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81879455,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9571999907493591,"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":0.9571999907493591,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.010700000450015068,"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":0.010400000028312206,"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/personalization","display_name":"Personalization","score":0.7159000039100647},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.48579999804496765},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.46889999508857727},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.45989999175071716},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.2896000146865845},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.2799000144004822}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7159000039100647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7074999809265137},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5482000112533569},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.48579999804496765},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44190001487731934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4196000099182129},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27399998903274536},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5393117070198059,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1533303231","https://openalex.org/W1971756658","https://openalex.org/W1998995907","https://openalex.org/W2029026153","https://openalex.org/W2049462786","https://openalex.org/W2123864036","https://openalex.org/W2146334809","https://openalex.org/W2156233592","https://openalex.org/W2169295472","https://openalex.org/W2599621350","https://openalex.org/W2893031943","https://openalex.org/W2962770129","https://openalex.org/W2972602947","https://openalex.org/W2999269393","https://openalex.org/W3015267357","https://openalex.org/W3095789936","https://openalex.org/W3169022486","https://openalex.org/W3198668286","https://openalex.org/W3210277894","https://openalex.org/W4221162793","https://openalex.org/W4236711558","https://openalex.org/W4252545733","https://openalex.org/W4285106979","https://openalex.org/W4286544676","https://openalex.org/W4361994820","https://openalex.org/W4385245566","https://openalex.org/W4392903872","https://openalex.org/W4392931630","https://openalex.org/W4393147046","https://openalex.org/W4402111222","https://openalex.org/W4402112365","https://openalex.org/W4404410676","https://openalex.org/W4415188578","https://openalex.org/W4416036822"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,44,75,88,96,109],"personalization":[4],"method":[5,89,137],"for":[6,29],"speech":[7],"emotion":[8,58],"recognition":[9],"(SER)":[10],"through":[11,100],"in-context":[12],"learning":[13],"(ICL).":[14],"Since":[15],"the":[16,31,80,114,135],"expression":[17],"of":[18,43,79],"emotions":[19],"varies":[20],"from":[21,113],"person":[22],"to":[23,52,56,64,69,90,116,119],"person,":[24],"speaker-specific":[25],"adaptation":[26],"is":[27,49,68,87],"crucial":[28],"improving":[30],"SER":[32,35,122,131],"performance.":[33],"Conventional":[34],"methods":[36],"have":[37],"been":[38],"personalized":[39,121],"using":[40,127],"emotional":[41,77],"utterances":[42,54,78],"target":[45,81],"speaker,":[46],"but":[47],"it":[48],"often":[50],"difficult":[51],"prepare":[53],"corresponding":[55],"all":[57],"labels":[59],"in":[60,83,102],"advance.":[61],"Our":[62],"idea":[63],"overcome":[65],"this":[66],"difficulty":[67],"obtain":[70],"speaker":[71,82],"characteristics":[72],"by":[73,94],"conditioning":[74,95],"few":[76,97],"ICL-based":[84],"inference.":[85],"ICL":[86],"perform":[91,120],"unseen":[92],"tasks":[93],"inputoutput":[98],"examples":[99],"inference":[101],"large":[103],"language":[104],"models":[105],"(LLMs).":[106],"We":[107],"meta-train":[108],"speech-language":[110],"model":[111],"extended":[112],"LLM":[115],"learn":[117],"how":[118],"via":[123],"ICL.":[124],"Experimental":[125],"results":[126],"our":[128],"newly":[129],"collected":[130],"dataset":[132],"demonstrate":[133],"that":[134],"proposed":[136],"outperforms":[138],"conventional":[139],"methods.":[140]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}