{"id":"https://openalex.org/W3148338017","doi":"https://doi.org/10.1109/icassp39728.2021.9414029","title":"RNN Transducer Models for Spoken Language Understanding","display_name":"RNN Transducer Models for Spoken Language Understanding","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3148338017","doi":"https://doi.org/10.1109/icassp39728.2021.9414029","mag":"3148338017"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414029","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/2104.03842","any_repository_has_fulltext":true},"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","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/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","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":"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","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/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","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/A5054462082","display_name":"Zvi Kons","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zvi Kons","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/A5053864983","display_name":"Ron Hoory","orcid":"https://orcid.org/0009-0006-1327-5160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ron Hoory","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":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7493","last_page":"7497"},"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":0.9987000226974487,"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":0.9986000061035156,"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":0.8587405681610107},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6312613487243652},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6150379180908203},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5813425183296204},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5422666072845459},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5405129790306091},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4650970697402954},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.45217397809028625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43796247243881226},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4122008681297302},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2650499939918518},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09955686330795288},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.06896105408668518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8587405681610107},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6312613487243652},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6150379180908203},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5813425183296204},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5422666072845459},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5405129790306091},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4650970697402954},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.45217397809028625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43796247243881226},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4122008681297302},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2650499939918518},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09955686330795288},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.06896105408668518},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414029","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:2104.03842","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.03842","pdf_url":"https://arxiv.org/pdf/2104.03842","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":"","raw_type":"text"},{"id":"mag:3148338017","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.03842","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.2104.03842","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.03842","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/cvfm-zf53","is_oa":true,"landing_page_url":"https://doi.org/10.17023/cvfm-zf53","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:2104.03842","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.03842","pdf_url":"https://arxiv.org/pdf/2104.03842","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3148338017.pdf","grobid_xml":"https://content.openalex.org/works/W3148338017.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1500614872","https://openalex.org/W1828163288","https://openalex.org/W2077302143","https://openalex.org/W2149980590","https://openalex.org/W2153338568","https://openalex.org/W2296073425","https://openalex.org/W2407080277","https://openalex.org/W2786839803","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2914417638","https://openalex.org/W2962760690","https://openalex.org/W2963288440","https://openalex.org/W2963414781","https://openalex.org/W2972327934","https://openalex.org/W2972574864","https://openalex.org/W2972584841","https://openalex.org/W2973040747","https://openalex.org/W2973127116","https://openalex.org/W2973229104","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/W3095552229","https://openalex.org/W3095776571","https://openalex.org/W3096251052","https://openalex.org/W3097964672","https://openalex.org/W3163300396","https://openalex.org/W6638749077","https://openalex.org/W6713762819","https://openalex.org/W6747398299","https://openalex.org/W6748263443","https://openalex.org/W6792406011"],"related_works":["https://openalex.org/W3161000786","https://openalex.org/W3093452977","https://openalex.org/W2949298366","https://openalex.org/W3098598562","https://openalex.org/W2928075308","https://openalex.org/W3004225838","https://openalex.org/W3132012095","https://openalex.org/W2977050317","https://openalex.org/W2981267975","https://openalex.org/W3157594170","https://openalex.org/W3133439430","https://openalex.org/W3095552229","https://openalex.org/W3015586639","https://openalex.org/W2805328873","https://openalex.org/W2073599923","https://openalex.org/W3161223924","https://openalex.org/W3096249532","https://openalex.org/W3029914199","https://openalex.org/W3174008653","https://openalex.org/W3108858638"],"abstract_inverted_index":{"We":[0,62],"present":[1],"a":[2,28,35,50,116],"comprehensive":[3],"study":[4],"on":[5,107],"building":[6],"and":[7,46,49,115,133],"adapting":[8],"RNN":[9],"transducer":[10],"(RNN-T)":[11],"models":[12,21,67,124,132],"for":[13],"spoken":[14],"language":[15],"understanding":[16],"(SLU).":[17],"These":[18],"end-to-end":[19],"(E2E)":[20],"are":[22,33,43,56],"constructed":[23],"in":[24],"three":[25],"practical":[26],"settings:":[27],"case":[29,37,53],"where":[30,38,54,87],"verbatim":[31],"transcripts":[32,55],"available,":[34,93],"constrained":[36],"the":[39,112,122,127],"only":[40],"available":[41,57],"annotations":[42],"SLU":[44,66,82,103,109],"labels":[45],"their":[47],"values,":[48],"more":[51],"restrictive":[52],"but":[58],"not":[59,92],"corresponding":[60],"audio.":[61],"show":[63],"how":[64],"RNN-T":[65],"can":[68],"be":[69],"developed":[70],"starting":[71],"from":[72],"pre-trained":[73],"automatic":[74],"speech":[75,96],"recognition":[76],"(ASR)":[77],"systems,":[78],"followed":[79],"by":[80],"an":[81],"adaptation":[83],"step.":[84],"In":[85],"settings":[86],"real":[88],"audio":[89],"data":[90,110,120],"is":[91,97],"artificially":[94],"synthesized":[95],"used":[98],"to":[99],"successfully":[100],"adapt":[101],"various":[102],"models.":[104],"When":[105],"evaluated":[106],"two":[108],"sets,":[111],"ATIS":[113],"corpus":[114],"customer":[117],"call":[118],"center":[119],"set,":[121],"proposed":[123],"closely":[125],"track":[126],"performance":[128],"of":[129],"other":[130],"E2E":[131],"achieve":[134],"state-of-the-art":[135],"results.":[136]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}