{"id":"https://openalex.org/W7148569416","doi":"https://doi.org/10.1109/asru65441.2025.11434787","title":"Speech in-context learning of paralinguistic tasks","display_name":"Speech in-context learning of paralinguistic tasks","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148569416","doi":"https://doi.org/10.1109/asru65441.2025.11434787"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434787","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/A5129705776","display_name":"Jeremy H. M. Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Jeremy H. M. Wong","raw_affiliation_strings":["Institute of Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112588637","display_name":"Muhammad Huzaifah","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Muhammad Huzaifah","raw_affiliation_strings":["Institute of Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132795316","display_name":"Nancy F. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nancy F. Chen","raw_affiliation_strings":["Institute of Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109309570","display_name":"Ai Ti Aw","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ai Ti Aw","raw_affiliation_strings":["Institute of Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5129705776"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81947242,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.2142000049352646,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.2142000049352646,"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/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.16120000183582306,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10730","display_name":"Language Development and Disorders","score":0.12790000438690186,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/paralanguage","display_name":"Paralanguage","score":0.9629999995231628},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5174999833106995},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.3589000105857849},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.34040001034736633},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.31619998812675476},{"id":"https://openalex.org/keywords/language-acquisition","display_name":"Language acquisition","score":0.3124000132083893}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9629999995231628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6567999720573425},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5910000205039978},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42170000076293945},{"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/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.299699991941452},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434787","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":[{"display_name":"Quality Education","score":0.4289790093898773,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2742542661","https://openalex.org/W2963686995","https://openalex.org/W3197742413","https://openalex.org/W3205644108","https://openalex.org/W4295936429","https://openalex.org/W4297841687","https://openalex.org/W4385823351","https://openalex.org/W4389010951","https://openalex.org/W4391021623","https://openalex.org/W4391021806","https://openalex.org/W4392902540","https://openalex.org/W4392931630","https://openalex.org/W4401246677","https://openalex.org/W4402111222","https://openalex.org/W4402112279","https://openalex.org/W4402670050","https://openalex.org/W4404781855","https://openalex.org/W4408354408","https://openalex.org/W4411119438","https://openalex.org/W7138431744"],"related_works":[],"abstract_inverted_index":{"In-context":[0],"learning":[1,58,96,132],"adapts":[2],"a":[3,8],"large":[4],"language":[5],"model":[6],"to":[7,43,47,55,111],"new":[9],"task,":[10],"without":[11],"computationally":[12],"expensive":[13],"parameter":[14],"updates.":[15],"This":[16,40],"has":[17],"previously":[18],"been":[19],"demonstrated":[20],"for":[21],"text":[22],"tasks,":[23],"as":[24,26,36],"well":[25],"speech":[27,60,77,94],"tasks":[28,61,70],"that":[29,62,85,134],"rely":[30],"primarily":[31],"on":[32,59,97],"lexical":[33],"information,":[34],"such":[35],"recognition":[37,79],"and":[38,76],"translation.":[39],"paper":[41],"proposes":[42],"extend":[44],"this":[45],"investigation":[46],"consider":[48],"the":[49,113,121],"ability":[50],"of":[51,66,71,93,116],"current":[52,86],"open-source":[53,87],"models":[54,88],"exhibit":[56,90],"in-context":[57,95,117,131],"require":[63],"an":[64],"understanding":[65],"paralinguistic":[67,98],"information.":[68],"The":[69,82],"stutter":[72],"detection,":[73],"pronunciation":[74],"assessment,":[75],"emotion":[78],"are":[80],"investigated.":[81],"results":[83],"suggest":[84],"already":[89],"some":[91],"degree":[92],"tasks.":[99],"To":[100],"more":[101],"fully":[102],"utilise":[103],"available":[104],"adaptation":[105],"data,":[106],"it":[107],"is":[108],"also":[109],"proposed":[110],"overcome":[112],"finite":[114],"number":[115],"exemplars":[118],"allowed":[119],"by":[120],"model\u2019s":[122],"prompt":[123],"length":[124],"limit,":[125],"through":[126],"ensemble":[127],"combination":[128],"over":[129],"multiple":[130],"runs":[133],"each":[135],"use":[136],"different":[137],"exemplars.":[138]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}
