{"id":"https://openalex.org/W4388937264","doi":"https://doi.org/10.1109/icccnt56998.2023.10306457","title":"Advancing Multimodal Fusion in Human-Computer Interaction: Integrating Eye Tracking, Lips Detection, Speech Recognition, and Voice Synthesis for Intelligent Cursor Control and Auditory Feedback","display_name":"Advancing Multimodal Fusion in Human-Computer Interaction: Integrating Eye Tracking, Lips Detection, Speech Recognition, and Voice Synthesis for Intelligent Cursor Control and Auditory Feedback","publication_year":2023,"publication_date":"2023-07-06","ids":{"openalex":"https://openalex.org/W4388937264","doi":"https://doi.org/10.1109/icccnt56998.2023.10306457"},"language":"en","primary_location":{"id":"doi:10.1109/icccnt56998.2023.10306457","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt56998.2023.10306457","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)","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/A5010906245","display_name":"Gayatri Jagnade","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gayatri Jagnade","raw_affiliation_strings":["Vishwakarma Institute of Technology,Department of Multidisciplinary Engineering,Pune,India","Department of Multidisciplinary Engineering, Vishwakarma Institute of Technology, Pune, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vishwakarma Institute of Technology,Department of Multidisciplinary Engineering,Pune,India","institution_ids":[]},{"raw_affiliation_string":"Department of Multidisciplinary Engineering, Vishwakarma Institute of Technology, Pune, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093323994","display_name":"Sunil Sable","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunil Sable","raw_affiliation_strings":["Vishwakarma Institute of Technology,Department of Chemical Engineering,Pune,India","Department of Chemical Engineering, Vishwakarma Institute of Technology, Pune, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vishwakarma Institute of Technology,Department of Chemical Engineering,Pune,India","institution_ids":[]},{"raw_affiliation_string":"Department of Chemical Engineering, Vishwakarma Institute of Technology, Pune, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013219346","display_name":"Mitesh Ikar","orcid":"https://orcid.org/0009-0006-1019-4963"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mitesh Ikar","raw_affiliation_strings":["Vishwakarma Institute of Technology,Department of Chemical Engineering,Pune,India","Department of Chemical Engineering, Vishwakarma Institute of Technology, Pune, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vishwakarma Institute of Technology,Department of Chemical Engineering,Pune,India","institution_ids":[]},{"raw_affiliation_string":"Department of Chemical Engineering, Vishwakarma Institute of Technology, Pune, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8712,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76082249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9962000250816345,"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":0.9962000250816345,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.7964005470275879},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.7072945237159729},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.499129056930542},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.48657333850860596},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.4403928816318512},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.43241819739341736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3434324860572815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33681827783584595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7964005470275879},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.7072945237159729},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.499129056930542},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.48657333850860596},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.4403928816318512},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.43241819739341736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3434324860572815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33681827783584595},{"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccnt56998.2023.10306457","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt56998.2023.10306457","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1990351874","https://openalex.org/W2079380854","https://openalex.org/W2104955141","https://openalex.org/W2159408788","https://openalex.org/W2184152089","https://openalex.org/W2329143390","https://openalex.org/W2391456535","https://openalex.org/W2530106226","https://openalex.org/W3017252933","https://openalex.org/W4322731614","https://openalex.org/W6675785006","https://openalex.org/W6686103888"],"related_works":["https://openalex.org/W2066003895","https://openalex.org/W2537963312","https://openalex.org/W2537762514","https://openalex.org/W2349788282","https://openalex.org/W577271088","https://openalex.org/W2120801881","https://openalex.org/W1982853263","https://openalex.org/W1974473538","https://openalex.org/W2020010749","https://openalex.org/W2796116650"],"abstract_inverted_index":{"In":[0],"the":[1,7,33,46,64,92,112,124,161,166,179,204,207,242,250,260,274,292],"realm":[2],"of":[3,9,48,67,108,163,184,206,252,262,276],"human-computer":[4,299],"interaction":[5,28,158,300],"(HCI),":[6],"integration":[8,47,162,261],"multiple":[10],"modalities":[11,69],"has":[12],"emerged":[13],"as":[14],"a":[15,143,154],"promising":[16],"approach":[17,279],"to":[18,62,70,80,150,224,231,233,249,280],"enhance":[19],"user":[20,97,129,151,173,235,244],"experiences":[21],"and":[22,26,39,55,75,89,99,131,156,175,188,198,219,237,269,285,297],"enable":[23,281],"more":[24,196,295],"natural":[25],"intuitive":[27,296],"paradigms.":[29,301],"This":[30,246],"paper":[31,247],"explores":[32],"advancements":[34],"in":[35,42,146,256],"multimodal":[36,209,253],"fusion":[37,210,254],"techniques":[38,255],"their":[40],"application":[41],"HCI,":[43],"focusing":[44],"on":[45],"eye":[49,85,102,263],"tracking,":[50,86,264],"lips":[51,87,113,265],"detection,":[52,88,266],"speech":[53,90,125,267],"recognition,":[54,91,268],"voice":[56,139,164,270],"synthesis.":[57,271],"The":[58,101,137,181,228],"proposed":[59,208],"framework":[60],"aims":[61],"leverage":[63],"combined":[65,182],"power":[66],"these":[68],"achieve":[71],"intelligent":[72,185,282],"cursor":[73,186,216,283],"control":[74,187,284],"provide":[76,286],"enhanced":[77],"auditory":[78,148,189,288],"feedback":[79,140,190],"users.":[81],"By":[82],"seamlessly":[83],"integrating":[84],"system":[93,167],"can":[94,168],"accurately":[95],"interpret":[96],"intentions":[98],"gestures.":[100],"tracking":[103,107],"component":[104,141],"enables":[105],"precise":[106],"gaze":[109],"movements,":[110],"while":[111],"detection":[114],"module":[115,127],"analyses":[116],"lip":[117],"movements":[118],"for":[119,195,294],"additional":[120],"input":[121,226],"signals.":[122],"Concurrently,":[123],"recognition":[126],"captures":[128],"commands":[130],"converts":[132],"them":[133],"into":[134],"actionable":[135],"instructions.":[136],"synthesized":[138],"plays":[142],"crucial":[144],"role":[145],"providing":[147],"responses":[149],"actions,":[152],"ensuring":[153],"seamless":[155],"engaging":[157],"experience.":[159,245],"Through":[160],"synthesis,":[165],"effectively":[169],"communicate":[170],"feedback,":[171,289],"confirm":[172],"inputs,":[174],"guide":[176],"users":[177],"through":[178],"interface.":[180],"functionality":[183],"opens":[191],"up":[192],"new":[193],"possibilities":[194],"efficient":[197],"immersive":[199,298],"HCI.":[200],"Experimental":[201],"evaluations":[202],"demonstrate":[203],"effectiveness":[205],"framework.":[211],"User":[212],"studies":[213],"reveal":[214],"improved":[215],"manipulation":[217],"accuracy":[218],"reduced":[220],"cognitive":[221],"load":[222],"compared":[223],"traditional":[225],"methods.":[227],"system's":[229],"ability":[230],"adapt":[232],"individual":[234],"preferences":[236],"environmental":[238],"conditions":[239],"further":[240],"enhances":[241],"overall":[243],"contributes":[248],"advancement":[251],"HCI":[257],"by":[258],"showcasing":[259],"It":[272],"highlights":[273],"potential":[275],"this":[277],"comprehensive":[278],"sophisticated":[287],"thereby":[290],"paving":[291],"way":[293]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
