{"id":"https://openalex.org/W4391021557","doi":"https://doi.org/10.1109/asru57964.2023.10389660","title":"Few-Shot Spoken Language Understanding Via Joint Speech-Text Models","display_name":"Few-Shot Spoken Language Understanding Via Joint Speech-Text Models","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021557","doi":"https://doi.org/10.1109/asru57964.2023.10389660"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5072923563","display_name":"Chung-Ming Chien","orcid":null},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chung-Ming Chien","raw_affiliation_strings":["Toyota Technological Institute at Chicago"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069651976","display_name":"Mingjiamei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingjiamei Zhang","raw_affiliation_strings":["The University of Chicago"],"affiliations":[{"raw_affiliation_string":"The University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049062211","display_name":"Ju-Chieh Chou","orcid":null},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ju-Chieh Chou","raw_affiliation_strings":["Toyota Technological Institute at Chicago"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["Toyota Technological Institute at Chicago"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072923563"],"corresponding_institution_ids":["https://openalex.org/I160992636"],"apc_list":null,"apc_paid":null,"fwci":0.5245,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73197855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.8170382380485535},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7424862384796143},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5347617864608765},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5226459503173828},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5032607913017273},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.48404449224472046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4437353014945984},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06707286834716797}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8170382380485535},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7424862384796143},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5347617864608765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5226459503173828},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5032607913017273},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.48404449224472046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4437353014945984},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06707286834716797},{"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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2747874407","https://openalex.org/W2896457183","https://openalex.org/W2914120296","https://openalex.org/W2952638691","https://openalex.org/W2958953787","https://openalex.org/W2970820321","https://openalex.org/W2970854433","https://openalex.org/W2972359262","https://openalex.org/W3016181583","https://openalex.org/W3036601975","https://openalex.org/W3037217258","https://openalex.org/W3103368673","https://openalex.org/W3122044994","https://openalex.org/W3140429000","https://openalex.org/W3156326119","https://openalex.org/W3169905056","https://openalex.org/W3180374548","https://openalex.org/W3205644108","https://openalex.org/W3207222250","https://openalex.org/W3209059054","https://openalex.org/W4221155340","https://openalex.org/W4223622550","https://openalex.org/W4226103796","https://openalex.org/W4226120743","https://openalex.org/W4226380987","https://openalex.org/W4237723258","https://openalex.org/W4281492411","https://openalex.org/W4283749766","https://openalex.org/W4287854499","https://openalex.org/W4287887773","https://openalex.org/W4297841873","https://openalex.org/W4310826357","https://openalex.org/W4312052802","https://openalex.org/W4313679638","https://openalex.org/W4319862218","https://openalex.org/W4323066695","https://openalex.org/W4323651091","https://openalex.org/W4372260307","https://openalex.org/W4375869005","https://openalex.org/W4377864748","https://openalex.org/W4378501656","https://openalex.org/W4385573012","https://openalex.org/W4385823328","https://openalex.org/W4392979802","https://openalex.org/W4394671563","https://openalex.org/W4394773771","https://openalex.org/W6755207826","https://openalex.org/W6765469073","https://openalex.org/W6767737316","https://openalex.org/W6776039324","https://openalex.org/W6780218876","https://openalex.org/W6790356757","https://openalex.org/W6796464841","https://openalex.org/W6803092890","https://openalex.org/W6810259195","https://openalex.org/W6845338303","https://openalex.org/W6846865774","https://openalex.org/W6847181065","https://openalex.org/W6847568899","https://openalex.org/W6848735303","https://openalex.org/W6850218400","https://openalex.org/W6850334629","https://openalex.org/W6852410838","https://openalex.org/W6853611000","https://openalex.org/W6854228366"],"related_works":["https://openalex.org/W4214877189","https://openalex.org/W2074502265","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2366718574","https://openalex.org/W4388696151","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2728912566","https://openalex.org/W2380471679"],"abstract_inverted_index":{"Recent":[0],"work":[1],"on":[2,60,86,108],"speech":[3,16,20,67,78,137],"representation":[4],"models":[5,58,106,131],"jointly":[6],"pre-trained":[7,52,105],"with":[8],"text":[9,22,61,139],"has":[10],"demonstrated":[11],"the":[12,37,114,120,126,146],"potential":[13],"of":[14,40,76,129],"improving":[15],"representations":[17,34,140],"by":[18],"encoding":[19],"and":[21,94,135,138],"in":[23,44],"a":[24,51,142],"shared":[25,33,143],"space.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30,55,117],"leverage":[31],"such":[32],"to":[35,66,100],"address":[36],"persistent":[38],"challenge":[39],"limited":[41],"data":[42],"availability":[43],"spoken":[45,87],"language":[46,88],"understanding":[47,89],"tasks.":[48],"By":[49],"employing":[50],"speech-text":[53,130],"model,":[54],"find":[56,124],"that":[57,125],"fine-tuned":[59,107],"can":[62],"be":[63],"effectively":[64],"transferred":[65],"testing":[68],"data.":[69,112],"With":[70],"as":[71,73],"little":[72],"1":[74],"hour":[75],"labeled":[77],"data,":[79],"our":[80],"proposed":[81],"approach":[82],"achieves":[83],"comparable":[84],"performance":[85],"tasks":[90],"(specifically,":[91],"sentiment":[92],"analysis":[93],"named":[95],"entity":[96],"recognition)":[97],"when":[98],"compared":[99],"previous":[101],"methods":[102],"using":[103],"speech-only":[104],"10":[109],"times":[110],"more":[111,150],"Beyond":[113],"proof-of-concept":[115],"study,":[116],"also":[118],"analyze":[119],"latent":[121],"representations.":[122],"We":[123],"bottom":[127],"layers":[128,148],"are":[132,149],"largely":[133],"task-agnostic":[134],"align":[136],"into":[141],"space,":[144],"while":[145],"top":[147],"task-specific.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}