{"id":"https://openalex.org/W4317382467","doi":"https://doi.org/10.1109/rivf55975.2022.10013914","title":"Human Voice Recognition for Subtitle Generators on Khmer and Vietnamese Newsletter Videos","display_name":"Human Voice Recognition for Subtitle Generators on Khmer and Vietnamese Newsletter Videos","publication_year":2022,"publication_date":"2022-12-20","ids":{"openalex":"https://openalex.org/W4317382467","doi":"https://doi.org/10.1109/rivf55975.2022.10013914"},"language":"en","primary_location":{"id":"doi:10.1109/rivf55975.2022.10013914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf55975.2022.10013914","pdf_url":null,"source":{"id":"https://openalex.org/S4363608274","display_name":"2022 RIVF International Conference on Computing and Communication Technologies (RIVF)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 RIVF International Conference on Computing and Communication Technologies (RIVF)","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/A5044245107","display_name":"An Cong Tran","orcid":"https://orcid.org/0000-0001-6184-909X"},"institutions":[{"id":"https://openalex.org/I177733328","display_name":"Can Tho University","ror":"https://ror.org/0071qz696","country_code":"VN","type":"education","lineage":["https://openalex.org/I177733328"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"An Cong Tran","raw_affiliation_strings":["Can Tho University,Can Tho City,Vietnam,900000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Can Tho University,Can Tho City,Vietnam,900000","institution_ids":["https://openalex.org/I177733328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021083069","display_name":"Loc Phuoc Son","orcid":null},"institutions":[{"id":"https://openalex.org/I177733328","display_name":"Can Tho University","ror":"https://ror.org/0071qz696","country_code":"VN","type":"education","lineage":["https://openalex.org/I177733328"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Loc Phuoc Son","raw_affiliation_strings":["Can Tho University,Can Tho City,Vietnam,900000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Can Tho University,Can Tho City,Vietnam,900000","institution_ids":["https://openalex.org/I177733328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059983639","display_name":"Duy Tuong Lam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duy Tuong Lam","raw_affiliation_strings":["Vietnam Television, VTV,Can Tho City,Vietnam,900000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vietnam Television, VTV,Can Tho City,Vietnam,900000","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088737329","display_name":"Nghi C. Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I177733328","display_name":"Can Tho University","ror":"https://ror.org/0071qz696","country_code":"VN","type":"education","lineage":["https://openalex.org/I177733328"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nghi Cong Tran","raw_affiliation_strings":["Can Tho University,Can Tho City,Vietnam,900000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Can Tho University,Can Tho City,Vietnam,900000","institution_ids":["https://openalex.org/I177733328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101729014","display_name":"H\u1ea3i Thanh Nguy\u1ec5n","orcid":"https://orcid.org/0000-0002-1386-1390"},"institutions":[{"id":"https://openalex.org/I177733328","display_name":"Can Tho University","ror":"https://ror.org/0071qz696","country_code":"VN","type":"education","lineage":["https://openalex.org/I177733328"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hai Thanh Nguyen","raw_affiliation_strings":["Can Tho University,Can Tho City,Vietnam,900000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Can Tho University,Can Tho City,Vietnam,900000","institution_ids":["https://openalex.org/I177733328"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1846,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42104539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"124","last_page":"129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9879000186920166,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/subtitle","display_name":"Subtitle","score":0.8218852877616882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8086817860603333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7502177953720093},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5820479989051819},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.5202054381370544},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4465022683143616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4191315174102783},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38552355766296387},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.21483248472213745},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15900176763534546},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13015961647033691}],"concepts":[{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.8218852877616882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8086817860603333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7502177953720093},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5820479989051819},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.5202054381370544},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4465022683143616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4191315174102783},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38552355766296387},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.21483248472213745},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15900176763534546},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13015961647033691},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rivf55975.2022.10013914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf55975.2022.10013914","pdf_url":null,"source":{"id":"https://openalex.org/S4363608274","display_name":"2022 RIVF International Conference on Computing and Communication Technologies (RIVF)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 RIVF International Conference on Computing and Communication Technologies (RIVF)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W46948191","https://openalex.org/W1907729166","https://openalex.org/W2023801476","https://openalex.org/W2059322891","https://openalex.org/W2136132422","https://openalex.org/W2191779130","https://openalex.org/W2792643794","https://openalex.org/W3013562487","https://openalex.org/W3048912752","https://openalex.org/W3103850820","https://openalex.org/W3110076758","https://openalex.org/W3157063407","https://openalex.org/W3174329270","https://openalex.org/W3217585508","https://openalex.org/W4205900877","https://openalex.org/W4285118713","https://openalex.org/W4285233746","https://openalex.org/W6601908271"],"related_works":["https://openalex.org/W2901286616","https://openalex.org/W3113733647","https://openalex.org/W4206924063","https://openalex.org/W2901718966","https://openalex.org/W3042674643","https://openalex.org/W3022757400","https://openalex.org/W1844055093","https://openalex.org/W61780229","https://openalex.org/W2077055222","https://openalex.org/W2973218968"],"abstract_inverted_index":{"Synchronization":[0],"of":[1,14,18,102,117,141],"subtitles":[2,45,142],"in":[3,9,28,38,51,63,106,119],"newsletters":[4,64],"or":[5],"ethnic":[6],"language":[7],"programs":[8],"videos":[10,33,65],"is":[11,34],"essential":[12],"because":[13],"the":[15,43,52,100,132,139],"linguistic":[16],"isolation":[17],"viewers":[19],"and":[20,47,74,84,90,127],"a":[21,80,85],"problem":[22],"for":[23],"broadcasters.":[24],"Human":[25],"voice":[26,121],"recognition":[27,108,122],"audio":[29],"extracted":[30],"from":[31],"newsletter":[32],"an":[35,57,115],"important":[36],"step":[37],"subtitle":[39,147],"synchronization":[40],"to":[41,59,137],"determine":[42],"time":[44],"appear":[46],"detect":[48],"human":[49,61,107,120],"voices":[50,62],"newsletter.":[53],"This":[54],"study":[55],"proposes":[56],"approach":[58],"detecting":[60],"through":[66],"pre-processing":[67],"techniques":[68],"such":[69],"as":[70],"Mel-frequency":[71],"cepstral":[72],"coefficients":[73],"training":[75],"on":[76,123],"deep":[77],"learning,":[78],"including":[79],"convolutional":[81],"neural":[82],"network":[83,87],"combined":[86],"between":[88],"convolution":[89],"Long":[91],"Short-Term":[92],"Memory":[93],"units.":[94],"In":[95],"addition,":[96],"we":[97],"also":[98],"examine":[99],"effects":[101],"selecting":[103],"hop":[104],"length":[105],"performances.":[109],"The":[110],"proposed":[111],"method":[112],"has":[113],"reached":[114],"accuracy":[116],"0.926":[118],"datasets":[124],"with":[125],"Khmer":[126],"Vietnamese":[128],"voices.":[129],"After":[130],"training,":[131],"model":[133],"results":[134],"are":[135],"expected":[136],"predict":[138],"appearance":[140],"files":[143],"that":[144],"efficiently":[145],"support":[146],"generators.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
