{"id":"https://openalex.org/W4392904787","doi":"https://doi.org/10.1109/icassp48485.2024.10447509","title":"Joint End-to-End Spoken Language Understanding and Automatic Speech Recognition Training Based on Unified Speech-to-Text Pre-Training","display_name":"Joint End-to-End Spoken Language Understanding and Automatic Speech Recognition Training Based on Unified Speech-to-Text Pre-Training","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904787","doi":"https://doi.org/10.1109/icassp48485.2024.10447509"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5007051105","display_name":"Eesung Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]},{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eesung Kim","raw_affiliation_strings":["Samsung Research America,USA","Samsung Research America, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research America,USA","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]},{"raw_affiliation_string":"Samsung Research America, USA","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101926294","display_name":"Yun Tang","orcid":"https://orcid.org/0000-0002-4075-5227"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]},{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Tang","raw_affiliation_strings":["Samsung Research America,USA","Samsung Research America, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research America,USA","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]},{"raw_affiliation_string":"Samsung Research America, USA","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026990708","display_name":"Taeyeon Ki","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]},{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taeyeon Ki","raw_affiliation_strings":["Samsung Research America,USA","Samsung Research America, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research America,USA","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]},{"raw_affiliation_string":"Samsung Research America, USA","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016640241","display_name":"Divya Neelagiri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]},{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divya Neelagiri","raw_affiliation_strings":["Samsung Research America,USA","Samsung Research America, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research America,USA","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]},{"raw_affiliation_string":"Samsung Research America, USA","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5094179019","display_name":"Vijendra Raj Apsingek","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]},{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijendra Raj Apsingek","raw_affiliation_strings":["Samsung Research America,USA","Samsung Research America, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research America,USA","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]},{"raw_affiliation_string":"Samsung Research America, USA","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]}],"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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10971","last_page":"10975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8945009112358093},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6915815472602844},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6675295829772949},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6159353256225586},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6107860803604126},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5444196462631226},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5344089269638062},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.47755321860313416},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.47744399309158325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47602444887161255},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4490051865577698},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4480375647544861},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4392739534378052},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.43128451704978943},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4174301028251648},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32225996255874634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8945009112358093},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6915815472602844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6675295829772949},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6159353256225586},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6107860803604126},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5444196462631226},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5344089269638062},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.47755321860313416},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.47744399309158325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47602444887161255},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4490051865577698},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4480375647544861},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4392739534378052},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.43128451704978943},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4174301028251648},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32225996255874634},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1649407914","https://openalex.org/W2894164357","https://openalex.org/W2896457183","https://openalex.org/W2963250244","https://openalex.org/W2972584841","https://openalex.org/W2995181338","https://openalex.org/W3034999214","https://openalex.org/W3036601975","https://openalex.org/W3049038774","https://openalex.org/W3100460087","https://openalex.org/W3148001440","https://openalex.org/W3155162503","https://openalex.org/W3161000786","https://openalex.org/W3161223924","https://openalex.org/W3211224152","https://openalex.org/W3217767527","https://openalex.org/W4223622550","https://openalex.org/W4285217170","https://openalex.org/W4296070421","https://openalex.org/W4297841571","https://openalex.org/W4297841597","https://openalex.org/W4319862213","https://openalex.org/W4385571440","https://openalex.org/W4385822501","https://openalex.org/W4385822624","https://openalex.org/W4385823346","https://openalex.org/W6780218876","https://openalex.org/W6803378298"],"related_works":["https://openalex.org/W4302360843","https://openalex.org/W3081187864","https://openalex.org/W2096389830","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W2916997151","https://openalex.org/W1499383998","https://openalex.org/W3198455051","https://openalex.org/W3133352777","https://openalex.org/W151018310"],"abstract_inverted_index":{"Modern":[0],"spoken":[1],"language":[2],"understanding":[3],"(SLU)":[4],"approaches":[5],"optimize":[6],"the":[7,38,66,84,108,119,130],"system":[8,52],"in":[9],"an":[10,50],"end-to-end":[11],"(E2E)":[12],"manner.":[13],"This":[14],"approach":[15],"offers":[16],"two":[17,57],"key":[18],"advantages.":[19],"Firstly,":[20],"it":[21,82],"helps":[22],"mitigate":[23],"error":[24],"propagation":[25],"from":[26,56],"upstream":[27],"systems.":[28],"Secondly,":[29],"combining":[30],"various":[31],"information":[32,55],"types":[33],"and":[34,61,63,77,80,99,104,112,144,152],"optimizing":[35,65],"them":[36],"towards":[37],"same":[39],"objective":[40],"is":[41,91],"straightforward.":[42],"In":[43,107],"this":[44],"study,":[45],"we":[46],"attempt":[47],"to":[48],"build":[49],"SLU":[51,86,89,100,113,126],"by":[53],"integrating":[54],"modalities,":[58],"i.e.,":[59],"speech":[60,76,96],"text,":[62],"concurrently":[64],"associated":[67],"tasks.":[68,87],"We":[69],"leverage":[70],"a":[71],"pre-trained":[72],"model":[73,90,121],"built":[74],"with":[75,94],"text":[78],"data":[79],"fine-tune":[81],"for":[83],"E2E":[85],"The":[88],"jointly":[92],"optimized":[93],"automatic":[95],"recognition":[97],"(ASR)":[98],"tasks":[101],"under":[102],"single-mode":[103,109],"dual-mode":[105],"schemes.":[106],"model,":[110],"ASR":[111,124],"results":[114],"are":[115],"predicted":[116],"sequentially,":[117],"whereas":[118],"dualmode":[120],"predicts":[122],"either":[123],"or":[125],"outputs":[127],"based":[128],"on":[129],"task":[131],"tag.":[132],"Our":[133],"proposed":[134],"method":[135],"demonstrates":[136],"its":[137],"superiority":[138],"through":[139],"benchmarking":[140],"against":[141],"FSC,":[142],"SLURP,":[143],"in-house":[145],"datasets,":[146],"exhibiting":[147],"improved":[148],"intent":[149],"accuracy,":[150],"SLU-F1,":[151],"Word":[153],"Error":[154],"Rate":[155],"(WER).":[156]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}