{"id":"https://openalex.org/W4224903522","doi":"https://doi.org/10.1109/icassp43922.2022.9746104","title":"Multi-Task RNN-T with Semantic Decoder for Streamable Spoken Language Understanding","display_name":"Multi-Task RNN-T with Semantic Decoder for Streamable Spoken Language Understanding","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224903522","doi":"https://doi.org/10.1109/icassp43922.2022.9746104"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746104","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5055157490","display_name":"Xuandi Fu","orcid":"https://orcid.org/0000-0002-9922-6856"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuandi Fu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102963746","display_name":"Feng-Ju Chang","orcid":"https://orcid.org/0000-0003-2405-3118"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng-Ju Chang","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023415990","display_name":"Martin Radfar","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Radfar","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101693020","display_name":"Kai Wei","orcid":"https://orcid.org/0000-0001-7068-6114"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Wei","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375136","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-4690-1886"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023708721","display_name":"Grant P. Strimel","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grant P. Strimel","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084035667","display_name":"Kanthashree Mysore Sathyendra","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kanthashree Mysore Sathyendra","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]}],"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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7507","last_page":"7511"},"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/T10028","display_name":"Topic Modeling","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/T12031","display_name":"Speech and dialogue systems","score":0.9994999766349792,"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":0.9024481177330017},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.7740150690078735},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.529392421245575},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4927883446216583},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4913620054721832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47607749700546265},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46648362278938293},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.465558797121048},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45638659596443176},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.38636884093284607},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3526943325996399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9024481177330017},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.7740150690078735},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.529392421245575},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4927883446216583},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4913620054721832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47607749700546265},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46648362278938293},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.465558797121048},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45638659596443176},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.38636884093284607},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3526943325996399},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746104","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1922655562","https://openalex.org/W2064675550","https://openalex.org/W2327501763","https://openalex.org/W2803392141","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2896457183","https://openalex.org/W2914417638","https://openalex.org/W2917128112","https://openalex.org/W2962784628","https://openalex.org/W2963288440","https://openalex.org/W2963974889","https://openalex.org/W2963979492","https://openalex.org/W2972584841","https://openalex.org/W3006974783","https://openalex.org/W3096109555","https://openalex.org/W3096589040","https://openalex.org/W3161223924","https://openalex.org/W3161302809","https://openalex.org/W3162313915","https://openalex.org/W3174008653","https://openalex.org/W3179843342","https://openalex.org/W3188372498","https://openalex.org/W4246962055","https://openalex.org/W6638749077","https://openalex.org/W6640090968","https://openalex.org/W6755207826","https://openalex.org/W6759393636","https://openalex.org/W6777513167","https://openalex.org/W6797942755"],"related_works":["https://openalex.org/W3174008653","https://openalex.org/W3138431698","https://openalex.org/W2962716343","https://openalex.org/W2765804957","https://openalex.org/W49594164","https://openalex.org/W2367925007","https://openalex.org/W3016262400","https://openalex.org/W4288099861","https://openalex.org/W43702919","https://openalex.org/W2139439365"],"abstract_inverted_index":{"End-to-end":[0],"Spoken":[1],"Language":[2,53],"Understanding":[3,54],"(E2E":[4],"SLU)":[5],"has":[6],"attracted":[7],"increasing":[8],"interest":[9],"due":[10],"to":[11,22,50,60,116,139,157],"its":[12],"advantages":[13],"of":[14,124],"joint":[15],"optimization":[16],"and":[17,67,148,152,163,178,197],"low":[18],"latency":[19,123],"when":[20],"compared":[21],"traditionally":[23],"cascaded":[24],"pipelines.":[25],"Existing":[26],"E2E":[27,191],"SLU":[28,126,177,192],"models":[29],"usually":[30],"follow":[31],"a":[32,44,51,133,154,170,179],"two-stage":[33,103,190],"configuration":[34],"where":[35],"an":[36,58,174],"Automatic":[37],"Speech":[38],"Recognition":[39],"(ASR)":[40],"network":[41],"first":[42],"predicts":[43,146],"transcript":[45,81],"which":[46,119],"is":[47,105],"then":[48],"passed":[49],"Natural":[52],"(NLU)":[55],"module":[56],"through":[57,169],"interface":[59],"infer":[61],"semantic":[62,136,155],"labels,":[63],"such":[64],"as":[65,108],"intent":[66],"slot":[68,164],"tags.":[69],"This":[70],"design,":[71],"however,":[72],"does":[73],"not":[74,106],"consider":[75],"the":[76,85,92,98,102,113,122,125,185,189],"NLU":[77,86,99,149,198],"posterior":[78],"while":[79,166],"making":[80],"predictions,":[82],"nor":[83],"correct":[84],"prediction":[87],"error":[88],"immediately":[89],"by":[90],"considering":[91],"previously":[93,160],"predicted":[94,161],"word-pieces.":[95],"In":[96,128],"addition,":[97],"model":[100,138,187,193],"in":[101],"system":[104],"streamable,":[107],"it":[109],"must":[110],"wait":[111],"for":[112,194],"audio":[114],"segments":[115],"complete":[117],"processing,":[118],"ultimately":[120],"impacts":[121],"system.":[127],"this":[129],"work,":[130],"we":[131,183],"propose":[132],"streamable":[134],"multi-task":[135],"transducer":[137],"address":[140],"these":[141],"considerations.":[142],"Our":[143],"proposed":[144,186],"architecture":[145],"ASR":[147,196],"labels":[150],"auto-regressively":[151],"uses":[153],"decoder":[156],"ingest":[158],"both":[159,195],"word-pieces":[162],"tags":[165],"aggregating":[167],"them":[168],"fusion":[171],"network.":[172],"Using":[173],"industry":[175],"scale":[176],"public":[180],"FSC":[181],"dataset,":[182],"show":[184],"outperforms":[188],"metrics.":[199]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}