{"id":"https://openalex.org/W4319862213","doi":"https://doi.org/10.1109/slt54892.2023.10023042","title":"Non-Autoregressive End-to-End Approaches for Joint Automatic Speech Recognition and Spoken Language Understanding","display_name":"Non-Autoregressive End-to-End Approaches for Joint Automatic Speech Recognition and Spoken Language Understanding","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862213","doi":"https://doi.org/10.1109/slt54892.2023.10023042"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023042","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5100716223","display_name":"Mohan Li","orcid":"https://orcid.org/0000-0002-2290-046X"},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210150981","display_name":"Toshiba (United States)","ror":"https://ror.org/051vpgk97","country_code":"US","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210150981"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Mohan Li","raw_affiliation_strings":["Toshiba Europe Ltd,Cambridge Research Laboratory","Cambridge Research Laboratory, Toshiba Europe Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Europe Ltd,Cambridge Research Laboratory","institution_ids":["https://openalex.org/I1292669757","https://openalex.org/I4210150981"]},{"raw_affiliation_string":"Cambridge Research Laboratory, Toshiba Europe Ltd","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086312107","display_name":"Rama Doddipatla","orcid":"https://orcid.org/0000-0003-1061-9512"},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210150981","display_name":"Toshiba (United States)","ror":"https://ror.org/051vpgk97","country_code":"US","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210150981"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Rama Doddipatla","raw_affiliation_strings":["Toshiba Europe Ltd,Cambridge Research Laboratory","Cambridge Research Laboratory, Toshiba Europe Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Europe Ltd,Cambridge Research Laboratory","institution_ids":["https://openalex.org/I1292669757","https://openalex.org/I4210150981"]},{"raw_affiliation_string":"Cambridge Research Laboratory, Toshiba Europe Ltd","institution_ids":["https://openalex.org/I1292669757"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0889,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77742313,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"390","last_page":"397"},"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":0.9979000091552734,"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":0.9962000250816345,"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":0.8191916942596436},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7807749509811401},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7027302980422974},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6954614520072937},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6590531468391418},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5583932995796204},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5465644598007202},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.535852313041687},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5197322368621826},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4977004826068878},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.49404314160346985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45390546321868896},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4241792559623718},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19899407029151917},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1317387819290161},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07019379734992981},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06351375579833984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8191916942596436},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7807749509811401},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7027302980422974},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6954614520072937},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6590531468391418},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5583932995796204},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5465644598007202},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.535852313041687},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5197322368621826},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4977004826068878},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.49404314160346985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45390546321868896},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4241792559623718},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19899407029151917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1317387819290161},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07019379734992981},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06351375579833984},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","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},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023042","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1649407914","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2137871902","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2747329762","https://openalex.org/W2892213699","https://openalex.org/W2894164357","https://openalex.org/W2917128112","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962826786","https://openalex.org/W2963288440","https://openalex.org/W2963341956","https://openalex.org/W2988975212","https://openalex.org/W3097777922","https://openalex.org/W3097882114","https://openalex.org/W3100460087","https://openalex.org/W3162249256","https://openalex.org/W3162899666","https://openalex.org/W3196500669","https://openalex.org/W3197140813","https://openalex.org/W3197697656","https://openalex.org/W3206573929","https://openalex.org/W4224917162","https://openalex.org/W4296070421","https://openalex.org/W4297683418","https://openalex.org/W4385245566","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6746208923","https://openalex.org/W6751425476","https://openalex.org/W6759393636","https://openalex.org/W6774835902","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W2529301793","https://openalex.org/W1732468982","https://openalex.org/W2384121599","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2284708545","https://openalex.org/W2916997151","https://openalex.org/W2949174760"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,37,58,60,66,72,90,95,126,135],"use":[4],"of":[5,65,113],"non-autoregressive":[6],"(NAR)":[7],"approaches":[8,81],"for":[9,84],"joint":[10],"automatic":[11],"speech":[12,38],"recognition":[13],"(ASR)":[14],"and":[15,62,77,102,109],"spoken":[16],"language":[17],"understanding":[18],"(SLU)":[19],"tasks.":[20],"The":[21],"proposed":[22,96],"NAR":[23,98,127],"systems":[24,128],"employ":[25],"a":[26,49,110,119],"Conformer":[27],"encoder":[28,51],"that":[29,94],"applies":[30],"connectionist":[31],"temporal":[32],"classification":[33],"(CTC)":[34],"to":[35,118],"transcribe":[36],"utterance":[39,67],"into":[40],"raw":[41],"ASR":[42,114],"hypotheses,":[43],"which":[44],"are":[45,68,82],"further":[46],"refined":[47],"with":[48],"bidirectional":[50],"representations":[52],"from":[53],"Transformers":[54],"(BERT)-like":[55],"decoder.":[56,74],"In":[57],"meantime,":[59],"intent":[61],"slot":[63],"labels":[64],"predicted":[69],"simultaneously":[70],"using":[71],"same":[73],"Both":[75],"Mask-CTC":[76],"self-conditioned":[78],"CTC":[79],"(SC-CTC)":[80],"explored":[83],"this":[85],"study.":[86],"Experiments":[87],"conducted":[88],"on":[89],"SLURP":[91],"dataset":[92],"show":[93],"SC-Mask-CTC":[97],"system":[99],"achieves":[100],"3.7%":[101],"3.2%":[103],"absolute":[104],"gains":[105],"in":[106],"SLU":[107],"metrics":[108],"competitive":[111],"level":[112],"accuracy,":[115],"when":[116],"compared":[117],"Conformer-Transformer":[120],"based":[121],"autoregressive":[122],"(AR)":[123],"model.":[124],"Additionally,":[125],"achieve":[129],"6\u00d7":[130],"faster":[131],"decoding":[132],"speed":[133],"than":[134],"AR":[136],"baseline.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}