{"id":"https://openalex.org/W7133302891","doi":"https://doi.org/10.1145/3742413.3789167","title":"VoiceAlign: A Shimming Layer for Enhancing the Usability of Legacy Voice User Interface Systems","display_name":"VoiceAlign: A Shimming Layer for Enhancing the Usability of Legacy Voice User Interface Systems","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133302891","doi":"https://doi.org/10.1145/3742413.3789167"},"language":null,"primary_location":{"id":"doi:10.1145/3742413.3789167","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742413.3789167","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3742413.3789167","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127889225","display_name":"Md Ehtesham-Ul-Haque","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Md Ehtesham-Ul-Haque","raw_affiliation_strings":["College of Information Sciences and Technology, Pennsylvania State University, University Park, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"College of Information Sciences and Technology, Pennsylvania State University, University Park, Pennsylvania, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005834738","display_name":"Syed Masum Billah","orcid":"https://orcid.org/0000-0001-5063-3808"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Syed Masum Billah","raw_affiliation_strings":["College of Information Sciences and Technology, Pennsylvania State University, University Park, Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"College of Information Sciences and Technology, Pennsylvania State University, University Park, Pennsylvania, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5127889225"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":44.7387,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.99526807,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1704","last_page":"1721"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12128","display_name":"AI in Service Interactions","score":0.45879998803138733,"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/T12128","display_name":"AI in Service Interactions","score":0.45879998803138733,"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":0.0674000009894371,"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/T13194","display_name":"ICT in Developing Communities","score":0.055799998342990875,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/timeout","display_name":"Timeout","score":0.6270999908447266},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.5812000036239624},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.5304999947547913},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5162000060081482},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.49779999256134033},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.39419999718666077},{"id":"https://openalex.org/keywords/setpoint","display_name":"Setpoint","score":0.37049999833106995},{"id":"https://openalex.org/keywords/interleaving","display_name":"Interleaving","score":0.3546999990940094},{"id":"https://openalex.org/keywords/formative-assessment","display_name":"Formative assessment","score":0.3479999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091999888420105},{"id":"https://openalex.org/C31691690","wikidata":"https://www.wikidata.org/wiki/Q1753979","display_name":"Timeout","level":2,"score":0.6270999908447266},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.5812000036239624},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5304999947547913},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5162000060081482},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.49779999256134033},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45159998536109924},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.39419999718666077},{"id":"https://openalex.org/C12302492","wikidata":"https://www.wikidata.org/wiki/Q1752097","display_name":"Setpoint","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.35670000314712524},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C42525527","wikidata":"https://www.wikidata.org/wiki/Q1209955","display_name":"Formative assessment","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C105446022","wikidata":"https://www.wikidata.org/wiki/Q445962","display_name":"Legacy system","level":3,"score":0.3224000036716461},{"id":"https://openalex.org/C2779305910","wikidata":"https://www.wikidata.org/wiki/Q5172809","display_name":"Corrective feedback","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C38956757","wikidata":"https://www.wikidata.org/wiki/Q716215","display_name":"Audio feedback","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C161615301","wikidata":"https://www.wikidata.org/wiki/Q309396","display_name":"Keystroke logging","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C190793597","wikidata":"https://www.wikidata.org/wiki/Q189768","display_name":"Application layer","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C2776303644","wikidata":"https://www.wikidata.org/wiki/Q1020499","display_name":"Interfacing","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3742413.3789167","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742413.3789167","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3742413.3789167","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742413.3789167","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6347470879554749,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G7312718072","display_name":null,"funder_award_id":"2326406","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W93888255","https://openalex.org/W201981411","https://openalex.org/W1823369059","https://openalex.org/W1993223663","https://openalex.org/W1995226545","https://openalex.org/W2009803366","https://openalex.org/W2012205861","https://openalex.org/W2041016355","https://openalex.org/W2041977675","https://openalex.org/W2044893557","https://openalex.org/W2092840718","https://openalex.org/W2119101732","https://openalex.org/W2124144842","https://openalex.org/W2149427207","https://openalex.org/W2157018518","https://openalex.org/W2165268962","https://openalex.org/W2280355185","https://openalex.org/W2610781091","https://openalex.org/W2796139395","https://openalex.org/W2889031479","https://openalex.org/W2899225656","https://openalex.org/W2916904544","https://openalex.org/W2942185243","https://openalex.org/W2942274440","https://openalex.org/W2962866211","https://openalex.org/W2965288462","https://openalex.org/W2966087730","https://openalex.org/W2979051136","https://openalex.org/W3003626793","https://openalex.org/W3011874043","https://openalex.org/W3029049378","https://openalex.org/W3040900470","https://openalex.org/W3119394424","https://openalex.org/W3127800809","https://openalex.org/W3206276539","https://openalex.org/W3210635777","https://openalex.org/W4220776662","https://openalex.org/W4234292174","https://openalex.org/W4240980716","https://openalex.org/W4301357669","https://openalex.org/W4302857920","https://openalex.org/W4309620206","https://openalex.org/W4386099614","https://openalex.org/W4389524378","https://openalex.org/W4390812815","https://openalex.org/W4396833729"],"related_works":[],"abstract_inverted_index":{"Voice":[0],"user":[1],"interfaces":[2],"(VUIs)":[3],"are":[4],"rapidly":[5],"transitioning":[6],"from":[7],"accessibility":[8],"features":[9],"to":[10,92,115],"mainstream":[11],"interaction":[12,189],"modalities.":[13],"Yet":[14],"most":[15],"operating":[16],"systems\u2019":[17],"built-in":[18],"voice":[19,88],"commands":[20,106,134],"remain":[21],"underutilized":[22,203],"despite":[23],"possessing":[24],"robust":[25],"technical":[26],"capabilities.":[27],"Through":[28],"our":[29,120,160],"analysis":[30],"of":[31,205],"four":[32],"commercial":[33],"VUI":[34,83,150,207],"systems":[35,208],"and":[36,60,81,102,137,141,162],"a":[37,98,108,155,164,214],"formative":[38],"study":[39],"with":[40,122,146,173],"16":[41],"participants,":[42,124],"we":[43,70,153],"found":[44],"that":[45,77,112,168],"fixed":[46],"command":[47,127],"formats":[48],"require":[49],"exact":[50],"phrasing,":[51],"restrictive":[52],"timeout":[53],"mechanisms":[54],"discard":[55],"input":[56],"during":[57],"planning":[58],"pauses,":[59],"insufficient":[61],"feedback":[62],"hampers":[63],"multi-step":[64],"interactions.":[65],"To":[66],"address":[67],"these":[68,104],"challenges,":[69],"developed":[71],"VoiceAlign,":[72],"an":[73,147],"adaptive":[74],"shimming":[75],"layer":[76],"mediates":[78],"between":[79],"users":[80],"legacy":[82,149,206],"systems.":[84],"VoiceAlign":[85,125],"intercepts":[86],"natural":[87],"commands,":[89],"transforms":[90],"them":[91],"match":[93],"the":[94,116,202],"required":[95,131],"syntax":[96],"using":[97],"large":[99],"language":[100,166],"model,":[101],"transmits":[103],"adapted":[105],"through":[107],"virtual":[109],"audio":[110],"channel":[111],"remains":[113],"transparent":[114],"underlying":[117],"system.":[118,151],"In":[119],"evaluation":[121],"12":[123],"reduced":[126],"failures":[128],"by":[129,159],"half,":[130],"25%":[132],"fewer":[133],"per":[135],"task,":[136],"significantly":[138],"lowered":[139],"cognitive":[140],"temporal":[142],"demands":[143],"when":[144,178],"paired":[145],"existing":[148,219],"Furthermore,":[152],"created":[154],"synthetic":[156],"dataset":[157],"informed":[158],"studies":[161],"fine-tuned":[163],"small":[165],"model":[167],"achieves":[169],"over":[170],"90%":[171],"accuracy":[172],"200":[174],"ms":[175],"response":[176],"time":[177],"served":[179],"locally,":[180],"eliminating":[181],"dependence":[182],"on":[183,190],"third-party":[184],"APIs":[185],"while":[186],"enabling":[187],"real-time":[188],"edge":[191],"devices.":[192],"This":[193],"work":[194],"demonstrates":[195],"how":[196],"modern":[197],"AI":[198],"techniques":[199],"can":[200],"unlock":[201],"potential":[204],"without":[209,217],"requiring":[210],"system":[211],"modifications,":[212],"offering":[213],"practical":[215],"solution":[216],"replacing":[218],"infrastructure.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-03-04T00:00:00"}
