{"id":"https://openalex.org/W4372269222","doi":"https://doi.org/10.1109/icassp49357.2023.10095055","title":"Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog History","display_name":"Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog History","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372269222","doi":"https://doi.org/10.1109/icassp49357.2023.10095055"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095055","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":"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/A5047892839","display_name":"Siddhant Arora","orcid":"https://orcid.org/0000-0003-0375-496X"},"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":"Siddhant Arora","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/A5034216052","display_name":"Hayato Futami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hayato Futami","raw_affiliation_strings":["Sony Group Corporation,Japan","Sony Group Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011937407","display_name":"Emiru Tsunoo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emiru Tsunoo","raw_affiliation_strings":["Sony Group Corporation,Japan","Sony Group Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021201726","display_name":"Brian Yan","orcid":null},"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":"Brian Yan","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"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":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.654,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66088323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T12031","display_name":"Speech and dialogue systems","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":0.9995999932289124,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8738037347793579},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8298516869544983},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.8175017833709717},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6724277138710022},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6450482606887817},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5916836261749268},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5903385281562805},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5657800436019897},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.49780797958374023},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.49155935645103455},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.47119638323783875},{"id":"https://openalex.org/keywords/semantic-interpretation","display_name":"Semantic interpretation","score":0.44261181354522705},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.4377084970474243},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36160027980804443},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2866487503051758},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16368511319160461},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1275801658630371}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8738037347793579},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8298516869544983},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.8175017833709717},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6724277138710022},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6450482606887817},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5916836261749268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5903385281562805},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5657800436019897},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.49780797958374023},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.49155935645103455},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.47119638323783875},{"id":"https://openalex.org/C193125573","wikidata":"https://www.wikidata.org/wiki/Q7449065","display_name":"Semantic interpretation","level":2,"score":0.44261181354522705},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.4377084970474243},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36160027980804443},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2866487503051758},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16368511319160461},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1275801658630371},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095055","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W14656806","https://openalex.org/W1972595521","https://openalex.org/W2004672974","https://openalex.org/W2043701535","https://openalex.org/W2058094241","https://openalex.org/W2098217544","https://openalex.org/W2120375264","https://openalex.org/W2144763279","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2473965551","https://openalex.org/W2509582621","https://openalex.org/W2526425061","https://openalex.org/W2736272491","https://openalex.org/W2896457183","https://openalex.org/W2931751229","https://openalex.org/W2935756939","https://openalex.org/W2952592807","https://openalex.org/W2962780374","https://openalex.org/W2963574857","https://openalex.org/W2972430654","https://openalex.org/W2972818416","https://openalex.org/W2979826702","https://openalex.org/W2997174602","https://openalex.org/W3005910077","https://openalex.org/W3095384101","https://openalex.org/W3096798607","https://openalex.org/W3097777922","https://openalex.org/W3162249256","https://openalex.org/W3162315798","https://openalex.org/W3163793923","https://openalex.org/W3197314576","https://openalex.org/W3198361190","https://openalex.org/W3209984917","https://openalex.org/W3217767527","https://openalex.org/W4225873749","https://openalex.org/W4226315417","https://openalex.org/W4287596060","https://openalex.org/W4295258045","https://openalex.org/W4295312788","https://openalex.org/W4297841571","https://openalex.org/W4385245566","https://openalex.org/W6674860264","https://openalex.org/W6739901393","https://openalex.org/W6751943214","https://openalex.org/W6755207826","https://openalex.org/W6755552547","https://openalex.org/W6761303817","https://openalex.org/W6766978945","https://openalex.org/W6768009688","https://openalex.org/W6784579990","https://openalex.org/W6785224828","https://openalex.org/W6803164887"],"related_works":["https://openalex.org/W2500779211","https://openalex.org/W48079147","https://openalex.org/W326836678","https://openalex.org/W4230258867","https://openalex.org/W2098498104","https://openalex.org/W4284683546","https://openalex.org/W2099383224","https://openalex.org/W1562973825","https://openalex.org/W1575088060","https://openalex.org/W2786839803"],"abstract_inverted_index":{"Most":[0],"human":[1],"interactions":[2],"occur":[3],"in":[4,24,42,80],"the":[5,11,20,98,126,135,154,166,198],"form":[6],"of":[7,14,157],"spoken":[8,25,136],"conversations":[9],"where":[10],"semantic":[12,32],"meaning":[13],"a":[15,115],"given":[16],"utterance":[17,23],"depends":[18],"on":[19,145],"context.":[21],"Each":[22],"conversation":[26],"can":[27,62,93,190],"be":[28],"represented":[29],"by":[30,87],"many":[31],"and":[33,36,83,107,132,149,189],"speaker":[34,130],"attributes,":[35,159],"there":[37],"has":[38,56],"been":[39],"an":[40,78,146,171],"interest":[41],"building":[43],"Spoken":[44],"Language":[45],"Understanding":[46],"(SLU)":[47],"systems":[48],"for":[49,72,134],"automatically":[50],"predicting":[51],"these":[52],"attributes.":[53],"Recent":[54],"work":[55],"shown":[57],"that":[58,119,139,179],"incorporating":[59,102],"dialogue":[60],"history":[61],"help":[63],"advance":[64],"SLU":[65,74,99,199],"performance.":[66],"However,":[67],"separate":[68],"models":[69],"are":[70],"used":[71],"each":[73],"task,":[75],"leading":[76],"to":[77,91,104,123,152,186,195],"increase":[79],"inference":[81],"time":[82],"computation":[84],"cost.":[85],"Motivated":[86],"this,":[88,112],"we":[89,94,113,150,168],"aim":[90],"ask:":[92],"jointly":[95,124],"model":[96,117,148,182],"all":[97],"tasks":[100],"while":[101],"context":[103,122,194],"facilitate":[105],"low-latency":[106],"lightweight":[108],"inference?":[109],"To":[110,164],"answer":[111],"propose":[114,170],"novel":[116],"architecture":[118],"learns":[120],"dialog":[121,128,158,193],"predict":[125],"intent,":[127],"act,":[129],"role,":[131],"emotion":[133],"utterance.":[137],"Note":[138],"our":[140,180],"joint":[141,181],"prediction":[142,155],"is":[143,161],"based":[144],"autoregressive":[147],"need":[151],"decide":[153],"order":[156,172],"which":[160],"not":[162],"trivial.":[163],"mitigate":[165],"issue,":[167],"also":[169],"agnostic":[173],"training":[174],"method.":[175],"Our":[176],"experiments":[177],"show":[178],"achieves":[183],"similar":[184],"results":[185],"task-specific":[187],"classifiers":[188],"effectively":[191],"integrate":[192],"further":[196],"improve":[197],"performance.1":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}