{"id":"https://openalex.org/W3162646066","doi":"https://doi.org/10.1109/icassp39728.2021.9414619","title":"Two-Stage Textual Knowledge Distillation for End-to-End Spoken Language Understanding","display_name":"Two-Stage Textual Knowledge Distillation for End-to-End Spoken Language Understanding","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162646066","doi":"https://doi.org/10.1109/icassp39728.2021.9414619","mag":"3162646066"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414619","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":"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/A5026308273","display_name":"Seongbin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seongbin Kim","raw_affiliation_strings":["Clova AI, NAVER Corp","Inha University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clova AI, NAVER Corp","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Inha University","institution_ids":["https://openalex.org/I191879574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001186750","display_name":"Gyuwan Kim","orcid":"https://orcid.org/0000-0002-5081-3945"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gyuwan Kim","raw_affiliation_strings":["Clova AI, NAVER Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clova AI, NAVER Corp","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045624301","display_name":"Seongjin Shin","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seongjin Shin","raw_affiliation_strings":["Clova AI, NAVER Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clova AI, NAVER Corp","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100319608","display_name":"Sangmin Lee","orcid":"https://orcid.org/0000-0002-3674-4701"},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangmin Lee","raw_affiliation_strings":["Inha University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inha University","institution_ids":["https://openalex.org/I191879574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"7463","last_page":"7467"},"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":0.9990000128746033,"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.894955575466156},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7109748721122742},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5889830589294434},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5421597957611084},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5160512328147888},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48014089465141296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46327635645866394},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44182610511779785},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.42676737904548645},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09283000230789185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.894955575466156},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7109748721122742},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5889830589294434},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5421597957611084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5160512328147888},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48014089465141296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46327635645866394},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44182610511779785},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42676737904548645},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09283000230789185},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414619","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":[{"id":"https://metadata.un.org/sdg/4","score":0.8500000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1821462560","https://openalex.org/W2193413348","https://openalex.org/W2786839803","https://openalex.org/W2795497335","https://openalex.org/W2803609229","https://openalex.org/W2842511635","https://openalex.org/W2891229414","https://openalex.org/W2895976713","https://openalex.org/W2896457183","https://openalex.org/W2898771141","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2962854302","https://openalex.org/W2963288440","https://openalex.org/W2963341956","https://openalex.org/W2964120993","https://openalex.org/W2965373594","https://openalex.org/W2972314145","https://openalex.org/W2972584841","https://openalex.org/W2972943112","https://openalex.org/W2977050317","https://openalex.org/W2979476256","https://openalex.org/W2996383576","https://openalex.org/W3011411500","https://openalex.org/W3015267417","https://openalex.org/W3015586639","https://openalex.org/W3015995734","https://openalex.org/W3038268361","https://openalex.org/W3049723069","https://openalex.org/W3092630929","https://openalex.org/W3096249532","https://openalex.org/W3096589040","https://openalex.org/W3097414768","https://openalex.org/W3176896803","https://openalex.org/W4297683418","https://openalex.org/W4297808394","https://openalex.org/W6638523607","https://openalex.org/W6687566353","https://openalex.org/W6748263443","https://openalex.org/W6750372648","https://openalex.org/W6751425476","https://openalex.org/W6754850772","https://openalex.org/W6755207826","https://openalex.org/W6755871579","https://openalex.org/W6766673545","https://openalex.org/W6768435644","https://openalex.org/W6769196770","https://openalex.org/W6771250757","https://openalex.org/W6776527912","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2020540721","https://openalex.org/W1483367581","https://openalex.org/W3107474891","https://openalex.org/W2953307569","https://openalex.org/W2547835662","https://openalex.org/W142374489","https://openalex.org/W2359001871","https://openalex.org/W2148757832","https://openalex.org/W1986021162","https://openalex.org/W4320194748"],"abstract_inverted_index":{"End-to-end":[0],"approaches":[1],"open":[2],"a":[3,53,79,96],"new":[4],"way":[5],"for":[6,29,162],"more":[7,48],"accurate":[8],"and":[9,63,71,86,111,134],"efficient":[10],"spoken":[11,163],"language":[12,164],"understanding":[13],"(SLU)":[14],"systems":[15],"by":[16,103],"alleviating":[17],"the":[18,92,118,121,130,137,142,155,159],"drawbacks":[19],"of":[20,66,107],"traditional":[21],"pipeline":[22],"systems.":[23],"Previous":[24],"works":[25],"exploit":[26],"textual":[27,46,55],"information":[28,47],"an":[30],"SLU":[31],"model":[32],"via":[33],"pre-training":[34,70],"with":[35,41,99],"automatic":[36],"speech":[37,80],"recognition":[38],"or":[39],"finetuning":[40],"knowledge":[42,56],"distillation.":[43],"To":[44],"utilize":[45],"effectively,":[49],"this":[50],"work":[51],"proposes":[52],"two-stage":[54],"distillation":[57],"method":[58],"that":[59,148],"matches":[60],"utterancelevel":[61],"representations":[62],"predicted":[64],"logits":[65],"two":[67],"modalities":[68],"during":[69],"fine-tuning,":[72],"sequentially.":[73],"We":[74],"use":[75],"vqwav2vec":[76],"BERT":[77],"as":[78],"encoder":[81],"because":[82],"it":[83],"captures":[84],"general":[85],"rich":[87],"features.":[88],"Furthermore,":[89],"we":[90,116,145],"improve":[91],"performance,":[93,157],"especially":[94],"in":[95,129,136],"low-resource":[97],"scenario,":[98],"data":[100],"augmentation":[101],"methods":[102,151],"randomly":[104],"masking":[105],"spans":[106],"discrete":[108],"audio":[109],"tokens":[110],"contextualized":[112],"hidden":[113],"representations.":[114],"Consequently,":[115],"push":[117],"state-of-the-art":[119],"on":[120],"Fluent":[122],"Speech":[123],"Commands,":[124],"achieving":[125],"99.7%":[126],"test":[127],"accuracy":[128],"full":[131],"dataset":[132],"setting":[133],"99.5%":[135],"10%":[138],"subset":[139],"setting.":[140],"Throughout":[141],"ablation":[143],"studies,":[144],"empirically":[146],"verify":[147],"all":[149],"used":[150],"are":[152],"crucial":[153],"to":[154],"final":[156],"providing":[158],"best":[160],"practice":[161],"understanding.":[165],"Code":[166],"is":[167],"available":[168],"at":[169],"https://github.com/clovaai/textual-kd-slu.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}