{"id":"https://openalex.org/W3206227170","doi":"https://doi.org/10.1145/3462244.3479902","title":"What\u2019s This? A Voice and Touch Multimodal Approach for Ambiguity Resolution in Voice Assistants","display_name":"What\u2019s This? A Voice and Touch Multimodal Approach for Ambiguity Resolution in Voice Assistants","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3206227170","doi":"https://doi.org/10.1145/3462244.3479902","mag":"3206227170"},"language":"en","primary_location":{"id":"doi:10.1145/3462244.3479902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462244.3479902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"article","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/A5100609347","display_name":"Jaewook Lee","orcid":"https://orcid.org/0000-0002-1481-9290"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jaewook Lee","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037537018","display_name":"Sebasti\u00e1n Rodr\u00edguez","orcid":"https://orcid.org/0000-0002-7003-1764"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sebastian S. Rodriguez","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045127536","display_name":"Raahul Natarrajan","orcid":null},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raahul Natarrajan","raw_affiliation_strings":["Vanderbilt University, USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101693761","display_name":"Jacqueline Chen","orcid":"https://orcid.org/0000-0002-9896-6262"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacqueline Chen","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049516481","display_name":"Harsh Deep","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harsh Deep","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009386988","display_name":"Alex Kirlik","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Kirlik","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100609347"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.9857,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.81068692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"512","last_page":"520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T12128","display_name":"AI in Service Interactions","score":0.9983999729156494,"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":0.9860000014305115,"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":0.7912750244140625},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6579952836036682},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6207729578018188},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5695375204086304},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5551611185073853},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.5441021919250488},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.5128481984138489},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.484524667263031},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45722758769989014},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41229236125946045},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3696274757385254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3106098473072052}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7912750244140625},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6579952836036682},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6207729578018188},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5695375204086304},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5551611185073853},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.5441021919250488},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.5128481984138489},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.484524667263031},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45722758769989014},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41229236125946045},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3696274757385254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3106098473072052},{"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3462244.3479902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462244.3479902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W172711948","https://openalex.org/W597039002","https://openalex.org/W1967661515","https://openalex.org/W1980150050","https://openalex.org/W1995678974","https://openalex.org/W2025530819","https://openalex.org/W2086458350","https://openalex.org/W2110228188","https://openalex.org/W2115040353","https://openalex.org/W2131588614","https://openalex.org/W2157289187","https://openalex.org/W2488114773","https://openalex.org/W2607719644","https://openalex.org/W2749424389","https://openalex.org/W2813057208","https://openalex.org/W2890735031","https://openalex.org/W2898076813","https://openalex.org/W2920996501","https://openalex.org/W2943686508","https://openalex.org/W2990860652","https://openalex.org/W3000666106","https://openalex.org/W3012624518","https://openalex.org/W3031942796","https://openalex.org/W3097959996","https://openalex.org/W3100756752","https://openalex.org/W3122197089","https://openalex.org/W3158011797","https://openalex.org/W4235494587","https://openalex.org/W4245990317","https://openalex.org/W4250337847"],"related_works":["https://openalex.org/W2066003895","https://openalex.org/W2537963312","https://openalex.org/W2537762514","https://openalex.org/W2349788282","https://openalex.org/W2353179089","https://openalex.org/W577271088","https://openalex.org/W2120801881","https://openalex.org/W1982853263","https://openalex.org/W1974473538","https://openalex.org/W2020010749"],"abstract_inverted_index":{"Human":[0],"speech":[1],"often":[2],"contains":[3],"ambiguity":[4,173],"stemming":[5],"from":[6],"the":[7,78,80,121,150,203,210,214,243,248],"use":[8,179],"of":[9,25,127,251],"demonstrative":[10],"pronouns":[11],"(DPs),":[12],"such":[13,40,53,61],"as":[14,41,62,117,167,202],"\u201cthis\u201d":[15],"and":[16,44,93,98,119,132,148,185,246],"\u201cthese.\u201d":[17],"While":[18],"we":[19,96,199],"can":[20,67,145,193],"typically":[21],"decipher":[22],"which":[23],"objects":[24],"interest":[26],"DPs":[27,180,239],"are":[28,46],"referring":[29],"to":[30,49,57,77,85,110,115,161,171,240],"based":[31],"on":[32],"context,":[33],"modern":[34],"day":[35],"voice":[36,103],"assistants":[37],"(VAs":[38],"\u2013":[39],"Google":[42],"Assistant":[43],"Siri)":[45],"yet":[47],"unable":[48],"process":[50],"queries":[51],"containing":[52],"ambiguity.":[54],"For":[55],"instance,":[56],"humans,":[58],"a":[59,74,100,154,159,190],"question":[60],"\u201chow":[63],"much":[64],"is":[65],"this?\u201d":[66],"be":[68],"clarified":[69],"through":[70,153],"visual":[71],"reference":[72],"(e.g.,":[73],"buyer":[75],"gestures":[76],"seller":[79],"object":[81,130],"they":[82],"would":[83],"like":[84],"purchase).":[86],"To":[87],"bridge":[88],"this":[89,197],"gap":[90],"between":[91],"human":[92],"machine":[94],"cognition,":[95],"built":[97],"examined":[99],"touch":[101,165],"+":[102],"multimodal":[104,211,244],"VA":[105,191,212,216,245],"prototype":[106,124],"that":[107,141,192,201],"enables":[108],"users":[109,178,188,208],"select":[111],"key":[112],"spatial":[113],"information":[114],"embed":[116],"context":[118],"query":[120,204],"VA.":[122],"The":[123],"converts":[125],"results":[126],"mobile,":[128],"real-time":[129],"recognition":[131,135],"optical":[133],"character":[134],"models":[136],"into":[137],"augmented":[138],"reality":[139],"buttons":[140],"represent":[142],"features.":[143],"Users":[144],"interact":[146,241],"with":[147,183,237,242],"modify":[149],"selected":[151],"features":[152],"word":[155],"grid.":[156],"We":[157],"conducted":[158],"study":[160],"investigate:":[162],"1)":[163],"how":[164,177,187],"performs":[166],"an":[168],"additional":[169],"modality":[170],"resolve":[172],"in":[174],"queries,":[175],"2)":[176],"when":[181],"interacting":[182],"VAs,":[184],"3)":[186],"perceive":[189],"understand":[194],"DPs.":[195],"From":[196],"procedure":[198],"found":[200],"becomes":[205],"more":[206],"complex,":[207],"prefer":[209],"over":[213],"standard":[215],"without":[217],"experiencing":[218],"elevated":[219],"cognitive":[220],"load.":[221],"Additionally,":[222],"even":[223],"though":[224],"it":[225],"took":[226],"some":[227],"time":[228],"getting":[229],"used":[230],"to,":[231],"many":[232],"participants":[233],"eventually":[234],"became":[235],"comfortable":[236],"using":[238],"appreciated":[247],"improved":[249],"human-likeness":[250],"human-VA":[252],"conversations.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
