{"id":"https://openalex.org/W2997208288","doi":"https://doi.org/10.1109/icccnt45670.2019.8944591","title":"Real Time object detection and multilingual speech synthesis","display_name":"Real Time object detection and multilingual speech synthesis","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2997208288","doi":"https://doi.org/10.1109/icccnt45670.2019.8944591","mag":"2997208288"},"language":"en","primary_location":{"id":"doi:10.1109/icccnt45670.2019.8944591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt45670.2019.8944591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 10th 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/A5035810645","display_name":"Okeke Stephen","orcid":"https://orcid.org/0000-0002-7495-6174"},"institutions":[{"id":"https://openalex.org/I102786147","display_name":"Dongseo University","ror":"https://ror.org/00wygsf57","country_code":"KR","type":"education","lineage":["https://openalex.org/I102786147"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Okeke Stephen","raw_affiliation_strings":["Department of Computer Engineering, Dongseo Univeristy, Busan, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Dongseo Univeristy, Busan, South Korea","institution_ids":["https://openalex.org/I102786147"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059053560","display_name":"Deepanjali Mishra","orcid":"https://orcid.org/0000-0002-5662-6999"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deepanjali Mishra","raw_affiliation_strings":["Department School of Humanities, KIT University, Bhubaneswar, Orissa, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department School of Humanities, KIT University, Bhubaneswar, Orissa, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023601908","display_name":"Mangal Sain","orcid":"https://orcid.org/0000-0001-7298-7930"},"institutions":[{"id":"https://openalex.org/I102786147","display_name":"Dongseo University","ror":"https://ror.org/00wygsf57","country_code":"KR","type":"education","lineage":["https://openalex.org/I102786147"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mangal Sain","raw_affiliation_strings":["Division of Computer Engineering, Dongseo University, Busan, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Computer Engineering, Dongseo University, Busan, South Korea","institution_ids":["https://openalex.org/I102786147"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4374,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.68582375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9975000023841858,"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":0.8542671799659729},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6254640221595764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5855770707130432},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.565171480178833},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5347539186477661},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5195191502571106},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5190185308456421},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.50962233543396},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.48736220598220825},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44678133726119995},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3622376322746277},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3519779443740845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8542671799659729},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6254640221595764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5855770707130432},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.565171480178833},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5347539186477661},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5195191502571106},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5190185308456421},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.50962233543396},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.48736220598220825},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44678133726119995},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3622376322746277},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3519779443740845},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccnt45670.2019.8944591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt45670.2019.8944591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1544407768","https://openalex.org/W1598866093","https://openalex.org/W2156303437","https://openalex.org/W2168231600","https://openalex.org/W2949382160","https://openalex.org/W2950635152","https://openalex.org/W2963542991","https://openalex.org/W3124149531"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W642007152","https://openalex.org/W4253660971","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W1909292483","https://openalex.org/W2052688117","https://openalex.org/W2550171623","https://openalex.org/W596245619"],"abstract_inverted_index":{"We":[0,76,104],"introduce":[1],"a":[2,23,39,56,79,85],"technique":[3],"for":[4,38,109,132,140],"real":[5,74,101],"time":[6],"deep":[7,81],"learning":[8,82,107],"based":[9,41],"image":[10,111],"detection":[11,112],"with":[12,50,84,94,145],"multilingual":[13],"neural":[14,42,57,87],"text-to-speech":[15],"(TTS)":[16],"synthesis;":[17],"to":[18,32,44],"generate":[19,91],"different":[20],"voices":[21,96],"from":[22],"single":[24,35,80,86],"model.":[25,123],"In":[26],"this":[27],"work,":[28],"we":[29],"show":[30,77],"improvement":[31,68],"the":[33,70,110,118,122,141],"existing":[34],"lingual":[36],"approach":[37],"single-model":[40],"text":[43],"speech":[45],"synthesis.":[46],"This":[47,124],"model,":[48],"constructed":[49],"higher":[51],"performance":[52],"building":[53],"block":[54],"of":[55,121],"network":[58],"(Inception4":[59],"model),":[60],"demonstrated":[61],"high":[62],"level":[63],"significant":[64],"audio":[65],"signal":[66],"quality":[67],"on":[69],"images":[71],"detected":[72],"in":[73,100],"life.":[75],"that":[78],"model":[83],"TTS":[88],"system":[89,131],"can":[90],"multiple":[92,146],"languages":[93],"unique":[95],"and":[97,113,116,135],"display":[98],"them":[99],"life":[102],"environment.":[103],"adopted":[105],"transfer":[106],"method":[108],"recognition":[114],"purpose":[115],"retrained":[117],"top":[119],"layer":[120],"work":[125],"introduces":[126],"user":[127],"friendly":[128],"image-to-speech":[129],"tracking":[130],"easy":[133],"navigation":[134],"valuable":[136],"information":[137],"extraction":[138],"especially":[139],"visually":[142],"impaired":[143],"people":[144],"language":[147],"capabilities.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}