{"id":"https://openalex.org/W7225657474","doi":"https://doi.org/10.5281/zenodo.24078635","title":"AI-Based Indian Sign Language Recognition, Real-Time Speech Generation Using Deep Learning and Computer Vision","display_name":"AI-Based Indian Sign Language Recognition, Real-Time Speech Generation Using Deep Learning and Computer Vision","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225657474","doi":"https://doi.org/10.5281/zenodo.24078635"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24078635","doi":"https://doi.org/10.5281/zenodo.24078635","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24078635","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24078635","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161352383","display_name":"Megha H C, Maseeha Banu, Sneha, Tanushree M, Sinchana K G","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Megha H C, Maseeha Banu, Sneha, Tanushree M, Sinchana K G","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5161352383"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.0,"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"}},{"id":"https://openalex.org/T11285","display_name":"Hearing Impairment and Communication","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/indian-sign-language","display_name":"Indian Sign Language","score":0.9380000233650208},{"id":"https://openalex.org/keywords/sign-language-recognition","display_name":"sign language recognition","score":0.9539999961853027},{"id":"https://openalex.org/keywords/hand-gesture-recognition","display_name":"hand gesture recognition","score":0.875},{"id":"https://openalex.org/keywords/mediapipe-hands","display_name":"MediaPipe Hands","score":0.9150000214576721},{"id":"https://openalex.org/keywords/letter-recognition","display_name":"letter recognition","score":0.7860000133514404},{"id":"https://openalex.org/keywords/word-recognition","display_name":"word recognition","score":0.9860000014305115},{"id":"https://openalex.org/keywords/sentence-construction","display_name":"sentence construction","score":0.5929999947547913},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.8040000200271606},{"id":"https://openalex.org/keywords/speech-to-text","display_name":"speech-to-text","score":0.9900000095367432},{"id":"https://openalex.org/keywords/assistive-communication-technology","display_name":"assistive communication technology","score":0.5920000076293945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7617999911308289},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6751000285148621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6430000066757202},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6348000168800354},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.5640000104904175},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5613999962806702},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.558899998664856},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.54830002784729},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4050000011920929},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C2776737515","wikidata":"https://www.wikidata.org/wiki/Q14759","display_name":"American Sign Language","level":3,"score":0.310699999332428},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3050999939441681},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2728999853134155}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24078635","doi":"https://doi.org/10.5281/zenodo.24078635","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24078635","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},{"id":"doi:10.5281/zenodo.24078636","doi":"https://doi.org/10.5281/zenodo.24078636","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24078636","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24078635","doi":"https://doi.org/10.5281/zenodo.24078635","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24078635","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7153291762","https://openalex.org/W7155651680","https://openalex.org/W4410855878","https://openalex.org/W4417316208","https://openalex.org/W4410430196","https://openalex.org/W7146957829","https://openalex.org/W7162217209","https://openalex.org/W4391130078","https://openalex.org/W4414776835","https://openalex.org/W4392157017"],"abstract_inverted_index":{"Communication":[0],"between":[1],"people":[2,10],"who":[3,11],"use":[4],"Indian":[5],"Sign":[6],"Language":[7],"(ISL)":[8],"and":[9,33,39,64,83,98,110,118,126,163,168,172],"do":[12],"not":[13],"understand":[14],"it":[15],"can":[16],"be":[17],"challenging.":[18],"This":[19],"project":[20],"presents":[21],"a":[22,74,103,129,137],"camera-based":[23],"ISL":[24],"recognition":[25,164],"system":[26],"that":[27,70],"converts":[28,40,147],"hand":[29,53],"gestures":[30],"into":[31,43,150],"letters":[32,167],"words,":[34,169],"supports":[35],"rule-based":[36,130],"sentence":[37,138,170],"formation,":[38],"selected":[41],"sentences":[42],"speech.":[44],"OpenCV":[45],"processes":[46,99],"camera":[47],"frames,":[48],"while":[49],"MediaPipe":[50],"Hands":[51],"extracts":[52,93],"landmarks.":[54],"The":[55,78,90],"letter-recognition":[56],"module":[57,92,146],"uses":[58],"21":[59],"landmarks":[60],"with":[61,106],"X,":[62],"Y,":[63],"Z":[65],"coordinates,":[66],"producing":[67],"63":[68],"features":[69,95],"are":[71,124],"classified":[72],"using":[73,102,141],"Random":[75],"Forest":[76],"model.":[77],"dataset":[79],"contains":[80],"30,884":[81],"samples,":[82],"the":[84,134,155],"reported":[85],"accuracy":[86],"is":[87],"approximately":[88],"99.97%.":[89],"word-recognition":[91],"162":[94],"per":[96],"frame":[97],"16-frame":[100],"sequences":[101],"TensorFlow/Keras":[104],"architecture":[105],"Conv1D,":[107],"Multi-Head":[108],"Attention,":[109],"Transformer-based":[111],"components.":[112],"It":[113],"recognizes":[114],"23":[115],"predefined":[116],"words":[117,123],"achieves":[119],"87.67%":[120],"accuracy.":[121],"Recognized":[122],"stored":[125],"passed":[127],"to":[128],"sentence-formation":[131],"module,":[132],"where":[133],"user":[135],"selects":[136],"for":[139,166],"Text-to-Speech":[140],"pyttsx3.":[142],"An":[143],"integrated":[144],"Speech-to-Text":[145],"spoken":[148],"input":[149],"text,":[151],"supporting":[152],"communication":[153],"in":[154],"reverse":[156],"direction.":[157],"A":[158],"Tkinter":[159],"application":[160],"provides":[161],"learning":[162],"modes":[165],"recognition,":[171],"Speech-to-Text.":[173]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}