{"id":"https://openalex.org/W4406462014","doi":"https://doi.org/10.1109/slt61566.2024.10832156","title":"WHISMA: A Speech-LLM to Perform Zero-Shot Spoken Language Understanding","display_name":"WHISMA: A Speech-LLM to Perform Zero-Shot Spoken Language Understanding","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406462014","doi":"https://doi.org/10.1109/slt61566.2024.10832156"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5100716223","display_name":"Mohan Li","orcid":"https://orcid.org/0000-0002-2290-046X"},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Mohan Li","raw_affiliation_strings":["Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066876667","display_name":"Cong-Thanh Do","orcid":"https://orcid.org/0000-0003-1748-2846"},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cong-Thanh Do","raw_affiliation_strings":["Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062392738","display_name":"Simon Keizer","orcid":"https://orcid.org/0000-0003-0173-8966"},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Keizer","raw_affiliation_strings":["Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006981021","display_name":"Youmna Farag","orcid":"https://orcid.org/0000-0002-1532-5997"},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Youmna Farag","raw_affiliation_strings":["Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006032697","display_name":"Svetlana Stoyanchev","orcid":"https://orcid.org/0000-0002-8079-1652"},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Svetlana Stoyanchev","raw_affiliation_strings":["Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086312107","display_name":"Rama Doddipatla","orcid":"https://orcid.org/0000-0003-1061-9512"},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rama Doddipatla","raw_affiliation_strings":["Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Europe Ltd,Cambridge Research Laboratory,Cambridge,UK","institution_ids":["https://openalex.org/I4210143477"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100716223"],"corresponding_institution_ids":["https://openalex.org/I4210143477"],"apc_list":null,"apc_paid":null,"fwci":1.0878,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82772303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1115","last_page":"1122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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":0.7221984267234802},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6313026547431946},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5221990942955017},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49460527300834656},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4854903519153595},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.400616317987442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3412938714027405},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24875617027282715}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7221984267234802},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6313026547431946},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5221990942955017},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49460527300834656},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4854903519153595},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.400616317987442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3412938714027405},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24875617027282715},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"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/slt61566.2024.10832156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2972584841","https://openalex.org/W3036601975","https://openalex.org/W3100460087","https://openalex.org/W3176896803","https://openalex.org/W3197956630","https://openalex.org/W3198694222","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4253707770","https://openalex.org/W4319862213","https://openalex.org/W4320858545","https://openalex.org/W4386351448","https://openalex.org/W4386552581","https://openalex.org/W4388718054","https://openalex.org/W4389518985","https://openalex.org/W4391021623","https://openalex.org/W4391021647","https://openalex.org/W4391021666","https://openalex.org/W4392903956","https://openalex.org/W4401042470","https://openalex.org/W4402112556","https://openalex.org/W4402727764","https://openalex.org/W4404781855","https://openalex.org/W6780218876","https://openalex.org/W6796464841","https://openalex.org/W6796581206","https://openalex.org/W6800664022","https://openalex.org/W6847363464","https://openalex.org/W6849177959","https://openalex.org/W6849831075","https://openalex.org/W6855801281","https://openalex.org/W6856227084","https://openalex.org/W6857054612","https://openalex.org/W6859099255"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Speech":[0],"large":[1],"language":[2,35],"models":[3,10],"(speech-LLMs)":[4],"integrate":[5],"speech":[6,49],"and":[7,57],"text-based":[8],"foundation":[9],"to":[11,94,100,105],"provide":[12],"a":[13,18,30,61,65,88,110,128],"unified":[14],"framework":[15],"for":[16,33],"handling":[17],"wide":[19],"range":[20],"of":[21,68,91,131],"downstream":[22],"tasks.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27,108],"introduce":[28],"WHISMA,":[29],"speech-LLM":[31,125],"tailored":[32],"spoken":[34],"understanding":[36],"(SLU)":[37],"that":[38,74,120],"demonstrates":[39],"robust":[40],"performance":[41,82],"in":[42,60],"various":[43],"zero-shot":[44,79],"settings.":[45],"WHISMA":[46,75,121],"combines":[47],"the":[48,54,78,84,95],"encoder":[50],"from":[51],"Whisper":[52],"with":[53,127],"Llama-3":[55],"LLM,":[56],"is":[58],"fine-tuned":[59],"parameter-efficient":[62],"manner":[63],"on":[64,83],"comprehensive":[66],"collection":[67],"SLU-related":[69],"datasets.":[70],"Our":[71],"experiments":[72],"show":[73],"significantly":[76],"improves":[77],"slot":[80],"filling":[81],"SLURP":[85],"benchmark,":[86],"achieving":[87],"relative":[89,129],"gain":[90,130],"26.6%":[92],"compared":[93],"current":[96],"state-of-the-art":[97],"model.":[98],"Furthermore,":[99],"evaluate":[101],"WHISMA\u2019s":[102],"generalisation":[103],"capabilities":[104],"unseen":[106],"domains,":[107],"develop":[109],"new":[111],"task-agnostic":[112],"benchmark":[113],"named":[114],"SLU-GLUE.":[115],"The":[116],"evaluation":[117],"results":[118],"indicate":[119],"outperforms":[122],"an":[123],"existing":[124],"(Qwen-Audio)":[126],"33.0%.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}