{"id":"https://openalex.org/W4226201494","doi":"https://doi.org/10.1109/asru51503.2021.9688079","title":"Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understanding","display_name":"Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understanding","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4226201494","doi":"https://doi.org/10.1109/asru51503.2021.9688079"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688079","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"preprint","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/A5107950590","display_name":"Kai Wei","orcid":"https://orcid.org/0009-0008-4195-3277"},"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":true,"raw_author_name":"Kai Wei","raw_affiliation_strings":["Alexa Speech, Amazon"],"affiliations":[{"raw_affiliation_string":"Alexa Speech, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032785756","display_name":"Thanh Tran","orcid":"https://orcid.org/0000-0002-8262-2414"},"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":"Thanh Tran","raw_affiliation_strings":["Alexa Speech, Amazon"],"affiliations":[{"raw_affiliation_string":"Alexa Speech, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"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":["Alexa Speech, Amazon"],"affiliations":[{"raw_affiliation_string":"Alexa Speech, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","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":["Alexa Speech, Amazon"],"affiliations":[{"raw_affiliation_string":"Alexa Speech, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058763585","display_name":"Thejaswi Muniyappa","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":"Thejaswi Muniyappa","raw_affiliation_strings":["Alexa Speech, Amazon"],"affiliations":[{"raw_affiliation_string":"Alexa Speech, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375105","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-1727-6321"},"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":["Alexa Speech, Amazon"],"affiliations":[{"raw_affiliation_string":"Alexa Speech, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109046112","display_name":"Anirudh Raju","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":"Anirudh Raju","raw_affiliation_strings":["Alexa Speech, Amazon"],"affiliations":[{"raw_affiliation_string":"Alexa Speech, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053016497","display_name":"Ross McGowan","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":"Ross McGowan","raw_affiliation_strings":["Alexa Speech, Amazon"],"affiliations":[{"raw_affiliation_string":"Alexa Speech, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062762746","display_name":"Nathan Susanj","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":"Nathan Susanj","raw_affiliation_strings":["Alexa Speech, Amazon"],"affiliations":[{"raw_affiliation_string":"Alexa Speech, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110230355","display_name":"Ariya Rastrow","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":"Ariya Rastrow","raw_affiliation_strings":["Alexa Speech, Amazon"],"affiliations":[{"raw_affiliation_string":"Alexa Speech, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","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":["Alexa Speech, Amazon"],"affiliations":[{"raw_affiliation_string":"Alexa Speech, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5107950590"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24728972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"837","last_page":"844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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":0.8008173704147339},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6881049871444702},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6430272459983826},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6252888441085815},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.6190474033355713},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4521512985229492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4219014048576355},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41554468870162964},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4148113429546356},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41337424516677856},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4130632281303406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008173704147339},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6881049871444702},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6430272459983826},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6252888441085815},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.6190474033355713},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4521512985229492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4219014048576355},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41554468870162964},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4148113429546356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41337424516677856},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4130632281303406},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688079","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"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/W2016589492","https://openalex.org/W2064675550","https://openalex.org/W2473965551","https://openalex.org/W2798881773","https://openalex.org/W2810084418","https://openalex.org/W2886025712","https://openalex.org/W2886319145","https://openalex.org/W2936774411","https://openalex.org/W2952611190","https://openalex.org/W2962704885","https://openalex.org/W2962745521","https://openalex.org/W2962760690","https://openalex.org/W2963229292","https://openalex.org/W2963979492","https://openalex.org/W2970676059","https://openalex.org/W2972314145","https://openalex.org/W2972584841","https://openalex.org/W2977830552","https://openalex.org/W2998562534","https://openalex.org/W3007885288","https://openalex.org/W3008915885","https://openalex.org/W3015760975","https://openalex.org/W3015885816","https://openalex.org/W3016010032","https://openalex.org/W3049038774","https://openalex.org/W3095552229","https://openalex.org/W3126145531","https://openalex.org/W3161631007","https://openalex.org/W3197900814","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6640212811","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766210504","https://openalex.org/W6786908755","https://openalex.org/W6797942755"],"related_works":["https://openalex.org/W1226999","https://openalex.org/W881173","https://openalex.org/W10658944","https://openalex.org/W1479534","https://openalex.org/W16102324","https://openalex.org/W10050918","https://openalex.org/W18411711","https://openalex.org/W11675957","https://openalex.org/W4374573","https://openalex.org/W14478317"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2,41],"seen":[3],"significant":[4],"advances":[5],"in":[6,49],"end-to-end":[7],"(E2E)":[8],"spoken":[9,21],"language":[10,34],"understanding":[11,35],"(SLU)":[12],"systems,":[13,36],"which":[14],"directly":[15],"predict":[16],"intents":[17],"and":[18,51,75,100,122,128,140],"slots":[19],"from":[20],"audio.":[22],"While":[23],"dialogue":[24,76],"history":[25],"has":[26],"been":[27],"exploited":[28],"to":[29,92,105],"improve":[30],"conventional":[31],"text-based":[32],"natural":[33],"current":[37],"E2E":[38,61],"SLU":[39,62],"approaches":[40],"not":[42],"yet":[43],"incorporated":[44],"such":[45],"critical":[46],"contextual":[47,60],"signals":[48],"multi-turn":[50,86],"task-oriented":[52],"dialogues.":[53],"In":[54],"this":[55],"work,":[56],"we":[57],"propose":[58],"a":[59,67,85,106,114,136,149],"model":[63],"architecture":[64],"that":[65,142],"uses":[66],"multi-head":[68],"attention":[69],"mechanism":[70],"over":[71,148],"encoded":[72],"previous":[73],"utterances":[74,111],"acts":[77],"(actions":[78],"taken":[79],"by":[80,113,126],"the":[81,97],"voice":[82,115],"assistant)":[83],"of":[84,110],"dialogue.":[87],"We":[88,131],"detail":[89],"alternative":[90],"methods":[91],"integrate":[93],"these":[94],"contexts":[95],"into":[96],"state-ofthe-art":[98],"recurrent":[99],"transformer-based":[101],"models.":[102],"When":[103],"applied":[104],"large":[107],"de-identified":[108],"dataset":[109,139],"collected":[112],"assistant,":[116],"our":[117,143],"method":[118,144],"reduces":[119],"average":[120],"word":[121],"semantic":[123],"error":[124],"rates":[125],"10.8%":[127],"12.6%,":[129],"respectively.":[130],"also":[132],"present":[133],"results":[134],"on":[135],"publicly":[137],"available":[138],"show":[141],"significantly":[145],"improves":[146],"performance":[147],"noncontextual":[150],"baseline":[151]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-05-05T00:00:00"}
