{"id":"https://openalex.org/W3161223924","doi":"https://doi.org/10.1109/icassp39728.2021.9414922","title":"Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining","display_name":"Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161223924","doi":"https://doi.org/10.1109/icassp39728.2021.9414922","mag":"3161223924"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5010825170","display_name":"Cheng-I Lai","orcid":"https://orcid.org/0000-0002-2343-8596"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cheng-I Lai","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058729228","display_name":"Yung-Sung Chuang","orcid":"https://orcid.org/0000-0002-1723-5063"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yung-Sung Chuang","raw_affiliation_strings":["National Taiwan University,College of Electrical Engineering and Computer Science","College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University,College of Electrical Engineering and Computer Science","College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029566548","display_name":"Shang-Wen Li","orcid":"https://orcid.org/0000-0003-0656-9874"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shang-Wen Li","raw_affiliation_strings":["Amazon AI"],"affiliations":[{"raw_affiliation_string":"Amazon AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5010825170"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.3905,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.97111806,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7468","last_page":"7472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.8638262152671814},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.751088559627533},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6427947282791138},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.607601523399353},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6013688445091248},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.599148690700531},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5545309782028198},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5532160997390747},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5446687340736389},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.533899188041687},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4273451566696167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8638262152671814},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.751088559627533},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6427947282791138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.607601523399353},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6013688445091248},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.599148690700531},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5545309782028198},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5532160997390747},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5446687340736389},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.533899188041687},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4273451566696167},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":48,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1936920915","https://openalex.org/W2019116789","https://openalex.org/W2077302143","https://openalex.org/W2097550833","https://openalex.org/W2251599843","https://openalex.org/W2327501763","https://openalex.org/W2766219058","https://openalex.org/W2803609229","https://openalex.org/W2806429264","https://openalex.org/W2842511635","https://openalex.org/W2889201969","https://openalex.org/W2894164357","https://openalex.org/W2896457183","https://openalex.org/W2917128112","https://openalex.org/W2936774411","https://openalex.org/W2963250244","https://openalex.org/W2963288440","https://openalex.org/W2963341956","https://openalex.org/W2963446094","https://openalex.org/W2964117975","https://openalex.org/W2971351151","https://openalex.org/W2972584841","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2973133192","https://openalex.org/W2977838803","https://openalex.org/W2979722627","https://openalex.org/W2981458636","https://openalex.org/W2982223350","https://openalex.org/W3015267417","https://openalex.org/W3015412890","https://openalex.org/W3036601975","https://openalex.org/W3049038774","https://openalex.org/W3092630929","https://openalex.org/W3095552229","https://openalex.org/W3096249532","https://openalex.org/W3097414768","https://openalex.org/W3099782249","https://openalex.org/W3099944122","https://openalex.org/W4289564002","https://openalex.org/W4297808394","https://openalex.org/W6640440542","https://openalex.org/W6752437113","https://openalex.org/W6755207826","https://openalex.org/W6759393636","https://openalex.org/W6769457076","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2073713056","https://openalex.org/W3110702597","https://openalex.org/W2125620709","https://openalex.org/W2110441383","https://openalex.org/W2045932760","https://openalex.org/W4233149903","https://openalex.org/W2326878701","https://openalex.org/W4293864700","https://openalex.org/W2184228419","https://openalex.org/W67445448"],"abstract_inverted_index":{"Much":[0],"recent":[1],"work":[2],"on":[3,20,43,95,114,150,163],"Spoken":[4],"Language":[5],"Understanding":[6],"(SLU)":[7],"is":[8,79,179,189],"limited":[9,97,183],"in":[10,172],"at":[11],"least":[12],"one":[13],"of":[14,47,99,185],"three":[15],"ways:":[16],"models":[17,28,40],"were":[18,29,41],"trained":[19,30,42],"oracle":[21,168],"text":[22,169],"input":[23,160,171],"and":[24,57,86,93,117,145,181],"neglected":[25],"ASR":[26,85,110,123],"errors,":[27],"to":[31,60,73],"predict":[32],"only":[33],"intents":[34],"without":[35],"the":[36,109,122],"slot":[37],"values,":[38],"or":[39,70],"a":[44,55,96,182],"large":[45],"amount":[46,98,184],"in-house":[48],"data.":[49,102],"In":[50,132],"this":[51],"paper,":[52],"we":[53,134],"propose":[54],"clean":[56],"general":[58],"framework":[59,78,156],"learn":[61],"semantics":[62,147,173,187],"directly":[63],"from":[64,68],"speech":[65,72,127,158],"with":[66,125,157,165],"semi-supervision":[67],"transcribed":[69,115],"untranscribed":[71],"address":[74],"these":[75],"issues.":[76],"Our":[77],"built":[80],"upon":[81],"pretrained":[82],"end-to-end":[83],"(E2E)":[84],"self-supervised":[87,126],"language":[88],"models,":[89],"such":[90,129],"as":[91,130,159,170],"BERT,":[92],"fine-tuned":[94],"target":[100],"SLU":[101,141,155],"We":[103],"study":[104],"two":[105,136],"semi-supervised":[106],"settings":[107],"for":[108,139,191],"component:":[111],"supervised":[112],"pretraining":[113,119],"speech,":[116],"unsupervised":[118],"by":[120],"replacing":[121],"encoder":[124],"representations,":[128],"wav2vec.":[131],"parallel,":[133],"identify":[135],"essential":[137],"criteria":[138],"evaluating":[140],"models:":[142],"environmental":[143,177],"noise-robustness":[144],"E2E":[146],"evaluation.":[148],"Experiments":[149],"ATIS":[151],"show":[152],"that":[153],"our":[154],"can":[161],"perform":[162],"par":[164],"those":[166],"using":[167],"understanding,":[174],"even":[175],"though":[176],"noise":[178],"present":[180],"labeled":[186],"data":[188],"available":[190],"training.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}