{"id":"https://openalex.org/W4372266921","doi":"https://doi.org/10.1109/icassp49357.2023.10096493","title":"A Two-Stage System for Spoken Language Understanding","display_name":"A Two-Stage System for Spoken Language Understanding","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266921","doi":"https://doi.org/10.1109/icassp49357.2023.10096493"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096493","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5102948484","display_name":"Gaosheng Zhang","orcid":"https://orcid.org/0000-0002-2800-7242"},"institutions":[{"id":"https://openalex.org/I4210087940","display_name":"Technology Holding (United States)","ror":"https://ror.org/005mr0595","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087940"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gaosheng Zhang","raw_affiliation_strings":["Shenzhen Transsion Holdings Co., Ltd,Shanghai Branch,China","Shanghai Branch, Shenzhen Transsion Holdings Co., Ltd, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Transsion Holdings Co., Ltd,Shanghai Branch,China","institution_ids":["https://openalex.org/I4210087940"]},{"raw_affiliation_string":"Shanghai Branch, Shenzhen Transsion Holdings Co., Ltd, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039381977","display_name":"Shilei Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087940","display_name":"Technology Holding (United States)","ror":"https://ror.org/005mr0595","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087940"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shilei Miao","raw_affiliation_strings":["Shenzhen Transsion Holdings Co., Ltd,Shanghai Branch,China","Shanghai Branch, Shenzhen Transsion Holdings Co., Ltd, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Transsion Holdings Co., Ltd,Shanghai Branch,China","institution_ids":["https://openalex.org/I4210087940"]},{"raw_affiliation_string":"Shanghai Branch, Shenzhen Transsion Holdings Co., Ltd, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070423029","display_name":"Linghui Tang","orcid":"https://orcid.org/0000-0003-2573-9912"},"institutions":[{"id":"https://openalex.org/I4210087940","display_name":"Technology Holding (United States)","ror":"https://ror.org/005mr0595","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087940"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linghui Tang","raw_affiliation_strings":["Shenzhen Transsion Holdings Co., Ltd,Shanghai Branch,China","Shanghai Branch, Shenzhen Transsion Holdings Co., Ltd, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Transsion Holdings Co., Ltd,Shanghai Branch,China","institution_ids":["https://openalex.org/I4210087940"]},{"raw_affiliation_string":"Shanghai Branch, Shenzhen Transsion Holdings Co., Ltd, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011928745","display_name":"Peijia Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087940","display_name":"Technology Holding (United States)","ror":"https://ror.org/005mr0595","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087940"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peijia Qian","raw_affiliation_strings":["Shenzhen Transsion Holdings Co., Ltd,Shanghai Branch,China","Shanghai Branch, Shenzhen Transsion Holdings Co., Ltd, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Transsion Holdings Co., Ltd,Shanghai Branch,China","institution_ids":["https://openalex.org/I4210087940"]},{"raw_affiliation_string":"Shanghai Branch, Shenzhen Transsion Holdings Co., Ltd, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102948484"],"corresponding_institution_ids":["https://openalex.org/I4210087940"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5234397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/computer-science","display_name":"Computer science","score":0.8512887954711914},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7925243377685547},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.7411172389984131},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.645355224609375},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6210073232650757},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5952044129371643},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5740086436271667},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5694851279258728},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5377445816993713},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5169034004211426},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.48824456334114075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4744965732097626},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.4579348564147949},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43183383345603943},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4308345317840576},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4270167946815491},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10750359296798706},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07075467705726624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8512887954711914},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7925243377685547},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7411172389984131},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.645355224609375},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6210073232650757},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5952044129371643},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5740086436271667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5694851279258728},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5377445816993713},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5169034004211426},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.48824456334114075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4744965732097626},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.4579348564147949},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43183383345603943},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4308345317840576},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4270167946815491},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10750359296798706},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07075467705726624},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096493","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2147880316","https://openalex.org/W2896457183","https://openalex.org/W2962784628","https://openalex.org/W4281779489","https://openalex.org/W4319862713","https://openalex.org/W6682082992","https://openalex.org/W6755207826","https://openalex.org/W6838276489","https://openalex.org/W6839924907"],"related_works":["https://openalex.org/W2131700956","https://openalex.org/W3174008653","https://openalex.org/W4288099861","https://openalex.org/W2893411096","https://openalex.org/W4213400064","https://openalex.org/W4390690247","https://openalex.org/W2139439365","https://openalex.org/W4224919006","https://openalex.org/W1484078554","https://openalex.org/W2006989109"],"abstract_inverted_index":{"In":[0,40,60,85],"this":[1],"paper,":[2],"we":[3,44,64,87],"propose":[4],"a":[5,46,106],"Two-Stage":[6],"system":[7],"for":[8,69],"SLU,":[9],"which":[10],"consists":[11],"of":[12,31,109,128],"Automatic":[13],"Speech":[14],"Recognition":[15],"(ASR)":[16],"tasks":[17],"and":[18,72,81,96,116],"Natural":[19],"Language":[20],"Understanding":[21,37],"(NLU)":[22],"tasks.":[23],"Our":[24],"work":[25],"is":[26],"done":[27],"in":[28],"the":[29,41,50,55,61,89,98,113,126],"context":[30],"an":[32,118],"ICASSP":[33],"2023":[34],"Spoken":[35],"Langauge":[36],"Grand":[38],"Challenge.":[39],"first":[42],"stage,":[43,63],"use":[45],"model":[47,114],"based":[48],"on":[49],"encoder-decoder":[51],"structure":[52],"to":[53,77,104],"recognize":[54],"speech":[56],"utterance":[57],"into":[58],"text.":[59],"second":[62],"combine":[65],"Bidirectional":[66],"Encoder":[67],"Representations":[68],"Transformers":[70],"(BERT)":[71],"Conditional":[73],"Random":[74],"Field":[75],"(CRF)":[76],"train":[78],"intent":[79],"determination":[80],"slot":[82],"filling":[83],"jointly.":[84],"addition,":[86],"compress":[88],"data":[90],"using":[91],"Byte":[92],"Pair":[93],"Encoding":[94],"(BPE)":[95],"construct":[97],"BERT":[99],"word":[100],"list":[101],"by":[102],"pre-training":[103],"save":[105],"large":[107],"number":[108],"parameters,":[110],"thus":[111],"extending":[112],"depth":[115],"obtaining":[117],"Exact":[119],"Match":[120],"boost.":[121],"The":[122],"final":[123],"experiments":[124],"demonstrate":[125],"effectiveness":[127],"our":[129],"proposed":[130],"model.":[131]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}