{"id":"https://openalex.org/W7133227390","doi":"https://doi.org/10.1145/3789514.3792054","title":"Beyond-Voice: Leveraging Articulatory Motion for Next-gen AI-Assistants","display_name":"Beyond-Voice: Leveraging Articulatory Motion for Next-gen AI-Assistants","publication_year":2026,"publication_date":"2026-02-25","ids":{"openalex":"https://openalex.org/W7133227390","doi":"https://doi.org/10.1145/3789514.3792054"},"language":null,"primary_location":{"id":"doi:10.1145/3789514.3792054","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3789514.3792054","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 27th International Workshop on Mobile Computing Systems and Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3789514.3792054","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075120384","display_name":"Tanmay Srivastava","orcid":"https://orcid.org/0000-0003-0144-7931"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanmay Srivastava","raw_affiliation_strings":["Stony Brook University, Stony Brook, USA"],"raw_orcid":"https://orcid.org/0000-0003-0144-7931","affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127780425","display_name":"Amartya Basu","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amartya Basu","raw_affiliation_strings":["Stony Brook University, Stony Brook, USA"],"raw_orcid":"https://orcid.org/0009-0004-8663-4828","affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127844828","display_name":"Shubham Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shubham Jain","raw_affiliation_strings":["Stony Brook University, Stony Brook, USA"],"raw_orcid":"https://orcid.org/0000-0002-4864-6420","affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, USA","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15068092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.274399995803833,"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":0.274399995803833,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.20720000565052032,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.13580000400543213,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/key","display_name":"Key (lock)","score":0.5921000242233276},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5789999961853027},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4205000102519989},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4189000129699707},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4002000093460083},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.310699999332428},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.30230000615119934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7099000215530396},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5921000242233276},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5789999961853027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.508899986743927},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5037999749183655},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4189000129699707},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3789514.3792054","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3789514.3792054","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 27th International Workshop on Mobile Computing Systems and Applications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3789514.3792054","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3789514.3792054","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 27th International Workshop on Mobile Computing Systems and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8481405873","display_name":"CAREER: Closed-loop Health Behavior Interventions in Multi-device Environments","funder_award_id":"2238553","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":7,"referenced_works":["https://openalex.org/W4255142548","https://openalex.org/W4294891788","https://openalex.org/W4387212757","https://openalex.org/W4395666765","https://openalex.org/W4403913173","https://openalex.org/W4405014344","https://openalex.org/W4415444972"],"related_works":[],"abstract_inverted_index":{"Current":[0],"Human-AI":[1,32],"speech":[2,28,82],"interfaces":[3,100],"are":[4],"limited":[5],"to":[6,108,113,136],"the":[7,11,22,123,128,131],"acoustic":[8,23],"signal,":[9],"overlooking":[10],"rich":[12],"information":[13],"in":[14],"articulatory":[15],"motion.":[16],"This":[17],"paper":[18],"explores":[19],"how":[20],"complementing":[21],"channel":[24,75],"with":[25,59,101],"signals":[26,47,55],"from":[27,110,144],"articulators":[29],"can":[30],"enhance":[31],"interaction.":[33],"Captured":[34],"via":[35],"a":[36,49,65,73,114],"range":[37],"of":[38,52,97,118],"sensors":[39],"(e.g.,":[40],"IMU,":[41],"EMG,":[42],"or":[43],"cameras),":[44],"these":[45,98],"non-acoustic":[46],"offer":[48],"new":[50],"layer":[51],"insight.":[53],"These":[54],"enable":[56],"applications":[57],"infeasible":[58],"audio":[60],"alone,":[61],"such":[62],"as":[63],"anticipating":[64],"user's":[66],"cognitive":[67],"struggle":[68],"before":[69],"they":[70],"speak,":[71],"maintaining":[72],"silent":[74],"for":[76],"private":[77],"human-AI":[78,119],"interaction,":[79],"providing":[80],"real-time":[81],"coaching,":[83],"and":[84,127],"even":[85],"monitoring":[86],"well-being":[87],"by":[88,141],"capturing":[89],"subtle":[90],"cues":[91],"like":[92],"jaw":[93],"clenching.":[94],"The":[95],"integration":[96],"\u201cbeyond-voice\u201d":[99],"large":[102],"language":[103],"models":[104],"presents":[105],"an":[106],"opportunity":[107],"move":[109],"voice-only":[111],"interactions":[112],"more":[115],"complete":[116],"model":[117],"communication.":[120],"We":[121],"outline":[122],"potential":[124],"research":[125,132],"directions":[126],"associated":[129],"challenges":[130],"community":[133],"must":[134],"address":[135],"realize":[137],"this":[138],"vision,":[139],"followed":[140],"key":[142],"takeaways":[143],"our":[145],"exploratory":[146],"study.":[147]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-03T00:00:00"}
