{"id":"https://openalex.org/W4226315417","doi":"https://doi.org/10.1109/icassp43922.2022.9747871","title":"Towards End-to-End Integration of Dialog History for Improved Spoken Language Understanding","display_name":"Towards End-to-End Integration of Dialog History for Improved Spoken Language Understanding","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4226315417","doi":"https://doi.org/10.1109/icassp43922.2022.9747871"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747871","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747871","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/A5113145191","display_name":"Vishal Sunder","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishal Sunder","raw_affiliation_strings":["The Ohio State University,Columbus,OH,USA","The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Columbus,OH,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM Research AI,NY,USA","IBM Research AI, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI,NY,USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM Research AI, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110252428","display_name":"Hong-Kwang Jeff Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong-Kwang J. Kuo","raw_affiliation_strings":["IBM Research AI,NY,USA","IBM Research AI, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI,NY,USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM Research AI, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037281393","display_name":"Jatin Ganhotra","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jatin Ganhotra","raw_affiliation_strings":["IBM Research AI,NY,USA","IBM Research AI, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI,NY,USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM Research AI, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Research AI,NY,USA","IBM Research AI, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI,NY,USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM Research AI, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["The Ohio State University,Columbus,OH,USA","The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Columbus,OH,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"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":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7497","last_page":"7501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/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/T10181","display_name":"Natural Language Processing Techniques","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/dialog-box","display_name":"Dialog box","score":0.9252809882164001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.838911235332489},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7205417156219482},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6514845490455627},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.6170897483825684},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5779464840888977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.57395339012146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5589924454689026},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5093992352485657},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49600133299827576},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49058952927589417},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4356445372104645},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17686909437179565},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16688081622123718},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1118054986000061}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9252809882164001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.838911235332489},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7205417156219482},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6514845490455627},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.6170897483825684},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5779464840888977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.57395339012146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5589924454689026},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5093992352485657},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49600133299827576},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49058952927589417},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4356445372104645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17686909437179565},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16688081622123718},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1118054986000061},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/icassp43922.2022.9747871","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747871","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":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W55328212","https://openalex.org/W1989996186","https://openalex.org/W2007261869","https://openalex.org/W2183112036","https://openalex.org/W2896457183","https://openalex.org/W2931751229","https://openalex.org/W2936774411","https://openalex.org/W2962745521","https://openalex.org/W2997174602","https://openalex.org/W3005910077","https://openalex.org/W3006901707","https://openalex.org/W3016006013","https://openalex.org/W3095384101","https://openalex.org/W3096589040","https://openalex.org/W3148001440","https://openalex.org/W3162875390","https://openalex.org/W3163300396","https://openalex.org/W3174321708","https://openalex.org/W3174525637","https://openalex.org/W3197314576","https://openalex.org/W3197900814","https://openalex.org/W3204494926","https://openalex.org/W4295258045","https://openalex.org/W4385245566","https://openalex.org/W6602256816","https://openalex.org/W6739901393","https://openalex.org/W6751943214","https://openalex.org/W6755207826","https://openalex.org/W6761303817","https://openalex.org/W6784579990","https://openalex.org/W6786908755","https://openalex.org/W6801909114"],"related_works":["https://openalex.org/W48079147","https://openalex.org/W2394821827","https://openalex.org/W2563921006","https://openalex.org/W1963944933","https://openalex.org/W1600043506","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W1977846844","https://openalex.org/W3156493709"],"abstract_inverted_index":{"Dialog":[0],"history":[1,25,76,133,145,149,171],"plays":[2],"an":[3,46,104,135,188],"important":[4],"role":[5],"in":[6,12,26,77,134],"spoken":[7],"language":[8],"understanding":[9],"(SLU)":[10],"performance":[11],"a":[13,35,65,98,115,148,197],"dialog":[14,24,75,132,141,161],"system.":[15],"For":[16],"end-to-end":[17],"(E2E)":[18],"SLU,":[19],"previous":[20],"work":[21],"has":[22],"used":[23],"text":[27],"form,":[28,79],"which":[29,49],"makes":[30],"the":[31,43,90,125,139,158,169,181],"model":[32,68,102,165,192],"dependent":[33],"on":[34,157],"cascaded":[36,173],"automatic":[37],"speech":[38,78],"recognizer":[39],"(ASR).":[40],"This":[41],"rescinds":[42],"benefits":[44],"of":[45,72,107,160,183,200],"E2E":[47,136,144],"system":[48],"is":[50,70],"intended":[51],"to":[52,57,122,186],"be":[53],"compact":[54],"and":[55,109],"robust":[56],"ASR":[58,189],"errors.":[59],"In":[60,180],"this":[61,194],"paper,":[62],"we":[63,119],"propose":[64,114],"hierarchical":[66],"conversation":[67,93,101],"that":[69,118],"capable":[71],"directly":[73],"using":[74],"making":[80],"it":[81],"fully":[82],"E2E.":[83],"We":[84,112],"also":[85,113],"distill":[86],"semantic":[87,110],"knowledge":[88],"from":[89],"available":[91],"gold":[92,184],"transcripts":[94,185],"by":[95,130,152,196],"jointly":[96],"training":[97,127],"similar":[99],"text-based":[100],"with":[103,124,168],"explicit":[105],"tying":[106],"acoustic":[108],"embeddings.":[111],"novel":[116],"technique":[117],"call":[120],"DropFrame":[121],"deal":[123],"long":[126],"time":[128],"incurred":[129],"adding":[131],"manner.":[137],"On":[138],"HarperValleyBank":[140],"dataset,":[142],"our":[143,191],"integration":[146],"outperforms":[147,193],"independent":[150],"baseline":[151,195],"7.7%":[153],"absolute":[154,202],"F1":[155,203],"score":[156],"task":[159],"action":[162],"recognition.":[163],"Our":[164],"performs":[166],"competitively":[167],"state-of-the-art":[170],"based":[172],"baseline,":[174],"but":[175],"uses":[176],"48%":[177],"fewer":[178],"parameters.":[179],"absence":[182],"fine-tune":[187],"model,":[190],"significant":[198],"margin":[199],"10%":[201],"score.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}