{"id":"https://openalex.org/W4225319488","doi":"https://doi.org/10.1109/icassp43922.2022.9747555","title":"Towards Reducing the Need for Speech Training Data to Build Spoken Language Understanding Systems","display_name":"Towards Reducing the Need for Speech Training Data to Build Spoken Language Understanding Systems","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225319488","doi":"https://doi.org/10.1109/icassp43922.2022.9747555"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747555","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110252428","display_name":"Hong-Kwang Jeff Kuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong-Kwang J. Kuo","raw_affiliation_strings":["IBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7932","last_page":"7936"},"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":0.9997000098228455,"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/T12031","display_name":"Speech and dialogue systems","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8949034214019775},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6644248366355896},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5901037454605103},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5811141133308411},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5416145920753479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4957471787929535},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4886091351509094},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47550636529922485},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.45022812485694885},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43720299005508423},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41148680448532104},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4113568067550659}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8949034214019775},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6644248366355896},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5901037454605103},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5811141133308411},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5416145920753479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4957471787929535},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4886091351509094},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47550636529922485},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.45022812485694885},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43720299005508423},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41148680448532104},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4113568067550659},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747555","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"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":32,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2077302143","https://openalex.org/W2153338568","https://openalex.org/W2786839803","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2914417638","https://openalex.org/W2936774411","https://openalex.org/W2937780860","https://openalex.org/W2962760690","https://openalex.org/W2963288440","https://openalex.org/W2963414781","https://openalex.org/W2972327934","https://openalex.org/W2972584841","https://openalex.org/W2973127116","https://openalex.org/W3007227084","https://openalex.org/W3015686596","https://openalex.org/W3015797571","https://openalex.org/W3015885816","https://openalex.org/W3016006013","https://openalex.org/W3016262400","https://openalex.org/W3095384101","https://openalex.org/W3095552229","https://openalex.org/W3095776571","https://openalex.org/W3096251052","https://openalex.org/W3097964672","https://openalex.org/W3161000786","https://openalex.org/W3163300396","https://openalex.org/W6638749077","https://openalex.org/W6747398299","https://openalex.org/W6781428138","https://openalex.org/W6784579990"],"related_works":["https://openalex.org/W2069592018","https://openalex.org/W2075740387","https://openalex.org/W2358990940","https://openalex.org/W2093931120","https://openalex.org/W2329812990","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361","https://openalex.org/W2096389830","https://openalex.org/W1499383998"],"abstract_inverted_index":{"The":[0,98],"lack":[1],"of":[2,34,72,100,127,140,150],"speech":[3,28,96,133,141],"data":[4,36],"annotated":[5],"with":[6,37,131],"labels":[7,39],"required":[8],"for":[9],"spoken":[10],"language":[11],"understanding":[12],"(SLU)":[13],"is":[14,104],"often":[15],"a":[16,48],"major":[17],"hurdle":[18],"in":[19],"building":[20],"end-to-end":[21],"(E2E)":[22],"systems":[23,59,91],"that":[24,55,77],"can":[25,80],"directly":[26],"process":[27],"inputs.":[29],"In":[30,43],"contrast,":[31],"large":[32],"amounts":[33,71],"text":[35,50,66],"suitable":[38],"are":[40],"usually":[41],"available.":[42],"this":[44],"paper,":[45],"we":[46,75],"propose":[47],"novel":[49],"representation":[51],"and":[52,109],"training":[53],"methodology":[54],"allows":[56],"E2E":[57],"SLU":[58,115],"to":[60,84,89,125,148],"be":[61,81],"effectively":[62],"constructed":[63],"using":[64,112],"these":[65,78,143],"resources.":[67],"With":[68,117,135],"very":[69],"limited":[70],"additional":[73,138],"speech,":[74],"show":[76],"models":[79,144],"further":[82,147],"improved":[83],"perform":[85],"at":[86],"levels":[87],"close":[88],"similar":[90],"built":[92],"on":[93,106],"the":[94,120,128],"full":[95,132,151],"datasets.":[97,116],"efficacy":[99],"our":[101],"proposed":[102,121],"approach":[103],"demonstrated":[105],"both":[107],"intent":[108],"entity":[110],"tasks":[111],"three":[113],"different":[114],"text-only":[118],"training,":[119],"system":[122],"achieves":[123],"up":[124],"90%":[126],"performance":[129],"possible":[130],"training.":[134],"just":[136],"an":[137],"10%":[139],"data,":[142],"significantly":[145],"improve":[146],"97%":[149],"performance.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}