{"id":"https://openalex.org/W4392931630","doi":"https://doi.org/10.1109/icassp48485.2024.10446502","title":"Can Whisper Perform Speech-Based In-Context Learning?","display_name":"Can Whisper Perform Speech-Based In-Context Learning?","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931630","doi":"https://doi.org/10.1109/icassp48485.2024.10446502"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446502","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/A5017974335","display_name":"Siyin Wang","orcid":"https://orcid.org/0009-0008-7992-2476"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyin Wang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"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/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao-Han Yang","raw_affiliation_strings":["Georgia Institute of Technology,School of Electrical and Computer Engineering,Atlanta,USA","School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Electrical and Computer Engineering,Atlanta,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014958566","display_name":"Ji Wu","orcid":"https://orcid.org/0000-0001-6170-726X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Wu","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460223","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-9583-0722"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13421","last_page":"13425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9921000003814697,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9883999824523926,"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/adaptability","display_name":"Adaptability","score":0.7353477478027344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7166604995727539},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7165253162384033},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7027414441108704},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.700217604637146},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5570608973503113},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5405025482177734},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5197122097015381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4521588683128357},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.41330739855766296},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.369393527507782},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14147347211837769},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08466550707817078}],"concepts":[{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.7353477478027344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7166604995727539},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7165253162384033},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7027414441108704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.700217604637146},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5570608973503113},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5405025482177734},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5197122097015381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4521588683128357},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41330739855766296},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.369393527507782},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14147347211837769},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08466550707817078},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446502","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1498717522","https://openalex.org/W2155770957","https://openalex.org/W2607719644","https://openalex.org/W2796873842","https://openalex.org/W2889494795","https://openalex.org/W2962893195","https://openalex.org/W2964099675","https://openalex.org/W3012624518","https://openalex.org/W3122241445","https://openalex.org/W3141961557","https://openalex.org/W3147107444","https://openalex.org/W3197295304","https://openalex.org/W4221160683","https://openalex.org/W4225808286","https://openalex.org/W4322718191","https://openalex.org/W4378105483","https://openalex.org/W4385567149","https://openalex.org/W4385572536","https://openalex.org/W4385573341","https://openalex.org/W4385822324","https://openalex.org/W4385822890","https://openalex.org/W4385822940","https://openalex.org/W4385823351","https://openalex.org/W4389010951","https://openalex.org/W4391021666","https://openalex.org/W4392903956","https://openalex.org/W6770813465","https://openalex.org/W6778883912","https://openalex.org/W6791446462","https://openalex.org/W6793191273","https://openalex.org/W6796581206","https://openalex.org/W6797716411","https://openalex.org/W6800875267","https://openalex.org/W6802728921","https://openalex.org/W6847363464","https://openalex.org/W6850625674","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W2387293848","https://openalex.org/W2250140200","https://openalex.org/W2944691285"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,8,33,100,107],"in-context":[4,21,90],"learning":[5,22],"abilities":[6],"of":[7,43,77,102],"Whisper":[9,75],"automatic":[10],"speech":[11,45,123],"recognition":[12,124],"(ASR)":[13],"models":[14,76],"released":[15],"by":[16],"OpenAI.":[17],"A":[18,88],"novel":[19],"speech-based":[20],"(SICL)":[23],"approach":[24],"is":[25,84],"proposed":[26],"for":[27],"test-time":[28],"adaptation,":[29],"which":[30,83,104],"can":[31,71,94,105],"reduce":[32],"word":[34,63],"error":[35],"rates":[36],"(WERs)":[37],"with":[38],"only":[39],"a":[40],"small":[41],"number":[42],"labelled":[44],"samples":[46],"without":[47],"gradient":[48],"descent.":[49],"Language-level":[50],"adaptation":[51,120],"experiments":[52],"using":[53,74,118],"Chinese":[54],"dialects":[55],"showed":[56],"that":[57],"when":[58],"applying":[59],"SICL":[60],"to":[61,97,112,139,145],"isolated":[62],"ASR,":[64],"consistent":[65],"and":[66,126,148],"considerable":[67,129],"relative":[68,109,130],"WER":[69,110,131],"reductions":[70],"be":[72,95],"achieved":[73,128],"any":[78],"size":[79],"on":[80,85,142],"two":[81],"dialects,":[82],"average":[86,108],"32.3%.":[87],"k-nearest-neighbours-based":[89],"example":[91],"selection":[92],"technique":[93],"applied":[96],"further":[98],"improve":[99],"efficiency":[101],"SICL,":[103],"increase":[106],"reduction":[111],"36.4%.":[113],"The":[114],"findings":[115],"are":[116,136],"verified":[117],"speaker":[119],"or":[121],"continuous":[122],"tasks,":[125],"both":[127],"reductions.":[132],"Detailed":[133],"quantitative":[134],"analyses":[135],"also":[137],"provided":[138],"shed":[140],"light":[141],"SICL\u2019s":[143],"adaptability":[144],"phonological":[146],"variances":[147],"dialect-specific":[149],"lexical":[150],"nuances.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}