{"id":"https://openalex.org/W2996724962","doi":"https://doi.org/10.1109/tencon.2019.8929263","title":"Speech Enabled Visual Question Answering using LSTM and CNN with Real Time Image Capturing for assisting the Visually Impaired","display_name":"Speech Enabled Visual Question Answering using LSTM and CNN with Real Time Image Capturing for assisting the Visually Impaired","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2996724962","doi":"https://doi.org/10.1109/tencon.2019.8929263","mag":"2996724962"},"language":"en","primary_location":{"id":"doi:10.1109/tencon.2019.8929263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon.2019.8929263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON)","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/A5042714718","display_name":"Annapurna P Patil","orcid":"https://orcid.org/0000-0003-4604-428X"},"institutions":[{"id":"https://openalex.org/I302410947","display_name":"M S Ramaiah University of Applied Sciences","ror":"https://ror.org/02anh8x74","country_code":"IN","type":"education","lineage":["https://openalex.org/I302410947"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Annapurna P. Patil","raw_affiliation_strings":["Dept of Computer Science and Engineering, Ramaiah Institute of Technology, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Dept of Computer Science and Engineering, Ramaiah Institute of Technology, Bangalore, India","institution_ids":["https://openalex.org/I302410947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030351143","display_name":"Amrita Behera","orcid":null},"institutions":[{"id":"https://openalex.org/I302410947","display_name":"M S Ramaiah University of Applied Sciences","ror":"https://ror.org/02anh8x74","country_code":"IN","type":"education","lineage":["https://openalex.org/I302410947"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Amrita Behera","raw_affiliation_strings":["Dept of Computer Science and Engineering, Ramaiah Institute of Technology, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Dept of Computer Science and Engineering, Ramaiah Institute of Technology, Bangalore, India","institution_ids":["https://openalex.org/I302410947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111070023","display_name":"Palagati Anusha","orcid":null},"institutions":[{"id":"https://openalex.org/I302410947","display_name":"M S Ramaiah University of Applied Sciences","ror":"https://ror.org/02anh8x74","country_code":"IN","type":"education","lineage":["https://openalex.org/I302410947"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"P Anusha","raw_affiliation_strings":["Dept of Computer Science and Engineering, Ramaiah Institute of Technology, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Dept of Computer Science and Engineering, Ramaiah Institute of Technology, Bangalore, India","institution_ids":["https://openalex.org/I302410947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005779974","display_name":"Mitali Seth","orcid":null},"institutions":[{"id":"https://openalex.org/I302410947","display_name":"M S Ramaiah University of Applied Sciences","ror":"https://ror.org/02anh8x74","country_code":"IN","type":"education","lineage":["https://openalex.org/I302410947"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mitali Seth","raw_affiliation_strings":["Dept of Computer Science and Engineering, Ramaiah Institute of Technology, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Dept of Computer Science and Engineering, Ramaiah Institute of Technology, Bangalore, India","institution_ids":["https://openalex.org/I302410947"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5098435488","display_name":"Prabhuling","orcid":null},"institutions":[{"id":"https://openalex.org/I302410947","display_name":"M S Ramaiah University of Applied Sciences","ror":"https://ror.org/02anh8x74","country_code":"IN","type":"education","lineage":["https://openalex.org/I302410947"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prabhuling","raw_affiliation_strings":["Dept of Computer Science and Engineering, Ramaiah Institute of Technology, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Dept of Computer Science and Engineering, Ramaiah Institute of Technology, Bangalore, India","institution_ids":["https://openalex.org/I302410947"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042714718"],"corresponding_institution_ids":["https://openalex.org/I302410947"],"apc_list":null,"apc_paid":null,"fwci":0.1012,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.46627266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2475","last_page":"2480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9973000288009644,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9950000047683716,"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/computer-science","display_name":"Computer science","score":0.8386350870132446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.645592212677002},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6237130761146545},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5143603086471558},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.4835336208343506},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4827639162540436},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.48174595832824707},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4616905450820923},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4549401104450226},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.44273698329925537},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43995437026023865},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.43646299839019775},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4234932065010071},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3852757513523102},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.367098331451416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8386350870132446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.645592212677002},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6237130761146545},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5143603086471558},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.4835336208343506},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4827639162540436},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.48174595832824707},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4616905450820923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4549401104450226},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.44273698329925537},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43995437026023865},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.43646299839019775},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4234932065010071},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3852757513523102},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.367098331451416},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tencon.2019.8929263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon.2019.8929263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1575833922","https://openalex.org/W1933349210","https://openalex.org/W1983927101","https://openalex.org/W2058556535","https://openalex.org/W2560730294","https://openalex.org/W2611470828","https://openalex.org/W2963890019","https://openalex.org/W6634232107","https://openalex.org/W7072257459"],"related_works":["https://openalex.org/W2168627904","https://openalex.org/W2515552481","https://openalex.org/W1570348318","https://openalex.org/W2015444353","https://openalex.org/W3013494979","https://openalex.org/W156769215","https://openalex.org/W4308101915","https://openalex.org/W2384605597","https://openalex.org/W3194047734","https://openalex.org/W4286432911"],"abstract_inverted_index":{"The":[0,53,94,139,148],"proposed":[1,54],"work":[2,95],"benefits":[3],"visually":[4,173],"impaired":[5,174],"individuals":[6],"in":[7,159],"identifying":[8],"objects":[9],"and":[10,35,65,78,86,104,110,119,126],"visualizing":[11],"scenarios":[12],"around":[13],"them":[14],"independent":[15],"of":[16,32,73,90,144],"any":[17,91],"external":[18],"support.":[19],"In":[20],"such":[21],"a":[22,28,97,113,128],"situation,":[23],"the":[24,33,48,124,132,137,162,172],"user":[25],"can":[26,150],"capture":[27],"real":[29],"time":[30],"image":[31,63,102,117],"surrounding":[34],"ask":[36],"an":[37,142,176],"open-ended":[38],"question,":[39,41],"classification":[40],"counting":[42],"question":[43,46,125],"or":[44],"yes/no":[45],"to":[47,61,75,83,135,154,178],"application":[49,55,163],"by":[50],"speech":[51,74,165],"input.":[52],"uses":[56,96],"Visual":[57],"Question":[58],"Answering":[59],"(VQA)":[60],"integrate":[62],"processing":[64,68],"natural":[66],"language":[67,105],"which":[69],"is":[70,164,168],"also":[71,151],"capable":[72],"text":[76],"translation":[77],"vice":[79],"versa":[80],"that":[81],"helps":[82],"identify,":[84],"recognize":[85],"thus":[87],"obtain":[88,136],"details":[89],"particular":[92],"image.":[93],"classical":[98],"CNN-LSTM":[99],"model":[100,140,149],"where":[101],"features":[103,106,118,134],"are":[107],"computed":[108],"separately":[109],"combined":[111,133],"at":[112],"later":[114],"stage":[115],"using":[116],"word":[120],"embedding":[121],"obtained":[122],"from":[123],"runs":[127],"multilayer":[129],"perceptron":[130],"on":[131],"results.":[138],"achieves":[141],"accuracy":[143],"57":[145],"per":[146],"cent.":[147],"be":[152],"utilized":[153],"develop":[155],"cognitive":[156],"interpretation":[157],"better":[158],"kids.":[160],"As":[161],"enabled":[166],"it":[167],"best":[169],"suited":[170],"for":[171],"with":[175],"easy":[177],"use":[179],"GUI.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}