{"id":"https://openalex.org/W3103753370","doi":"https://doi.org/10.1109/icassp39728.2021.9414522","title":"End-to-End Spoken Language Understanding Using Transformer Networks and Self-Supervised Pre-Trained Features","display_name":"End-to-End Spoken Language Understanding Using Transformer Networks and Self-Supervised Pre-Trained Features","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3103753370","doi":"https://doi.org/10.1109/icassp39728.2021.9414522","mag":"3103753370"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414522","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.08238","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079262240","display_name":"Edmilson Morais","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edmilson Morais","raw_affiliation_strings":["IBM Research AI","IBM research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]},{"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","IBM research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]},{"raw_affiliation_string":"IBM research AI","institution_ids":[]}]},{"author_position":"middle","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","IBM research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]},{"raw_affiliation_string":"IBM research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047353872","display_name":"Zolt\u00e1n T\u00fcske","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zoltan Tuske","raw_affiliation_strings":["IBM Research AI","IBM research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]},{"raw_affiliation_string":"IBM research AI","institution_ids":[]}]},{"author_position":"last","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","IBM research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]},{"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":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7483","last_page":"7487"},"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","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"}}],"keywords":[{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.8814554214477539},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8312708139419556},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7592799663543701},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5740149021148682},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5041252374649048},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4736158549785614},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.4192591905593872},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4164712131023407},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.4157960116863251},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39195719361305237},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3631207346916199},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.2540796399116516},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09851333498954773},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07818695902824402},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05738067626953125}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8814554214477539},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8312708139419556},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7592799663543701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5740149021148682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5041252374649048},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4736158549785614},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.4192591905593872},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4164712131023407},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.4157960116863251},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39195719361305237},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3631207346916199},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2540796399116516},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09851333498954773},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07818695902824402},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05738067626953125},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414522","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"},{"id":"pmh:oai:arXiv.org:2011.08238","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.08238","pdf_url":"https://arxiv.org/pdf/2011.08238","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3103753370","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.08238.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.08238","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.08238","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/qd8g-av02","is_oa":true,"landing_page_url":"https://doi.org/10.17023/qd8g-av02","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.08238","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.08238","pdf_url":"https://arxiv.org/pdf/2011.08238","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3103753370.pdf","grobid_xml":"https://content.openalex.org/works/W3103753370.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1614862348","https://openalex.org/W1623072288","https://openalex.org/W2575101493","https://openalex.org/W2784121710","https://openalex.org/W2787948962","https://openalex.org/W2885185669","https://openalex.org/W2894164357","https://openalex.org/W2896457183","https://openalex.org/W2904631866","https://openalex.org/W2928075308","https://openalex.org/W2949079242","https://openalex.org/W2949892141","https://openalex.org/W2963026768","https://openalex.org/W2963250244","https://openalex.org/W2963288440","https://openalex.org/W2963974889","https://openalex.org/W2972327934","https://openalex.org/W2972584841","https://openalex.org/W2979476256","https://openalex.org/W2982223350","https://openalex.org/W2982399380","https://openalex.org/W2998230451","https://openalex.org/W2998501909","https://openalex.org/W3025035610","https://openalex.org/W3035202887","https://openalex.org/W3036601975","https://openalex.org/W3037217258","https://openalex.org/W3041561163","https://openalex.org/W3049256661","https://openalex.org/W3080993257","https://openalex.org/W3090731342","https://openalex.org/W3095552229","https://openalex.org/W3097964672","https://openalex.org/W3099782249","https://openalex.org/W3154950814","https://openalex.org/W3209042722","https://openalex.org/W6631362777","https://openalex.org/W6636392717","https://openalex.org/W6732187701","https://openalex.org/W6755207826","https://openalex.org/W6756618220","https://openalex.org/W6769311223","https://openalex.org/W6772848563","https://openalex.org/W6777232839","https://openalex.org/W6780218876","https://openalex.org/W6780361010"],"related_works":["https://openalex.org/W3162875390","https://openalex.org/W3015412890","https://openalex.org/W3095698432","https://openalex.org/W3155162503","https://openalex.org/W3157594170","https://openalex.org/W3091835551","https://openalex.org/W3005915390","https://openalex.org/W3180180466","https://openalex.org/W3155427814","https://openalex.org/W3182811388","https://openalex.org/W3148757058","https://openalex.org/W3204316016","https://openalex.org/W3049256661","https://openalex.org/W3160016036","https://openalex.org/W3207222250","https://openalex.org/W2964161387","https://openalex.org/W3212799896","https://openalex.org/W3209984917","https://openalex.org/W3015522062","https://openalex.org/W3205550549"],"abstract_inverted_index":{"Transformer":[0],"networks":[1],"and":[2,60,69,87],"self-supervised":[3,52,95,104],"pre-training":[4],"have":[5],"consistently":[6],"delivered":[7],"state-of-art":[8],"results":[9],"in":[10,21,111,124],"the":[11,22,49,73,81,114,132],"field":[12,23],"of":[13,24,51,83,134],"natural":[14],"language":[15,26],"processing":[16],"(NLP);":[17],"however,":[18],"their":[19],"merits":[20],"spoken":[25],"understanding":[27],"(SLU)":[28],"still":[29],"need":[30],"further":[31],"investigation.":[32],"In":[33],"this":[34],"paper":[35],"we":[36],"introduce":[37],"a":[38],"modular":[39],"End-to-End":[40],"(E2E)":[41],"SLU":[42,64],"transformer":[43],"network":[44],"based":[45],"architecture":[46],"which":[47],"allows":[48],"use":[50],"pre-":[53],"trained":[54],"acoustic":[55,97,106],"features,":[56],"pre-trained":[57,84,96,105,135],"model":[58,85,136],"initialization":[59,86],"multi-task":[61,88,127],"training.":[62],"Several":[63],"experiments":[65,79],"for":[66],"predicting":[67],"intent":[68],"entity":[70],"labels/values":[71],"using":[72],"ATIS":[74],"dataset":[75],"are":[76,122],"performed.":[77],"These":[78],"investigate":[80],"interaction":[82],"training":[89],"with":[90,126],"either":[91],"traditional":[92],"filterbank":[93,109],"or":[94],"features.":[98],"Results":[99],"show":[100],"not":[101],"only":[102],"that":[103,118],"features":[107,110,121],"outperform":[108],"almost":[112,130],"all":[113],"experiments,":[115],"but":[116],"also":[117],"when":[119],"these":[120],"used":[123],"combination":[125],"training,":[128],"they":[129],"eliminate":[131],"necessity":[133],"initialization.":[137]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}