{"id":"https://openalex.org/W4402389847","doi":"https://doi.org/10.1109/mapr63514.2024.10660987","title":"Evaluation of Command and Speaker Recognition on Vietnamese Voice Dataset to Enhance Security","display_name":"Evaluation of Command and Speaker Recognition on Vietnamese Voice Dataset to Enhance Security","publication_year":2024,"publication_date":"2024-08-15","ids":{"openalex":"https://openalex.org/W4402389847","doi":"https://doi.org/10.1109/mapr63514.2024.10660987"},"language":"en","primary_location":{"id":"doi:10.1109/mapr63514.2024.10660987","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mapr63514.2024.10660987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","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/A5013479214","display_name":"Nhut Minh Ngo","orcid":"https://orcid.org/0009-0001-8827-334X"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Minh-Nhut Ngo","raw_affiliation_strings":["University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109779288","display_name":"Long-Quoc Le","orcid":null},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Long-Quoc Le","raw_affiliation_strings":["University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I23582244"],"apc_list":null,"apc_paid":null,"fwci":0.2778,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61944732,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9932000041007996,"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/T11309","display_name":"Music and Audio Processing","score":0.963699996471405,"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/vietnamese","display_name":"Vietnamese","score":0.851201057434082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7548471689224243},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7339208126068115},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7032970190048218},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4134218990802765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32977819442749023},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.060656726360321045}],"concepts":[{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.851201057434082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7548471689224243},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7339208126068115},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7032970190048218},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4134218990802765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32977819442749023},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.060656726360321045},{"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/mapr63514.2024.10660987","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mapr63514.2024.10660987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","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":32,"referenced_works":["https://openalex.org/W1999408164","https://openalex.org/W2133564696","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2402146185","https://openalex.org/W2481916066","https://openalex.org/W2625477228","https://openalex.org/W2766428625","https://openalex.org/W2797583228","https://openalex.org/W2808631503","https://openalex.org/W2888641632","https://openalex.org/W2965384495","https://openalex.org/W2969985801","https://openalex.org/W3013020904","https://openalex.org/W3024869864","https://openalex.org/W3025075133","https://openalex.org/W3097018422","https://openalex.org/W3119913666","https://openalex.org/W3126622195","https://openalex.org/W3163571828","https://openalex.org/W3196496149","https://openalex.org/W3198035615","https://openalex.org/W3201587918","https://openalex.org/W4288091954","https://openalex.org/W4297841773","https://openalex.org/W4385823030","https://openalex.org/W6679434410","https://openalex.org/W6748150159","https://openalex.org/W6750665317","https://openalex.org/W6754496211","https://openalex.org/W6769178842","https://openalex.org/W6789507654"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3,106],"work":[4],"in":[5,163],"building":[6],"a":[7,18,113,136],"Vietnamese":[8,47,169,181],"dataset":[9,152],"for":[10,60,156,207,216],"command":[11,73,159,170],"and":[12,94,102,129,153,160,190,194],"speaker":[13,161,182],"recognition":[14,74,83,171],"problems.":[15],"We":[16,38,91],"built":[17],"website":[19],"that":[20,65,118,144,211],"allows":[21],"users":[22,68,215],"of":[23,45,72,81,98,168,175,180,188],"mobile":[24],"devices":[25,64],"or":[26],"personal":[27],"computers":[28],"to":[29,32,120,158,204,213],"be":[30,202],"able":[31],"provide":[33],"their":[34,127],"voice":[35,100],"samples":[36],"easily.":[37],"collected":[39],"more":[40,50],"than":[41,51,79],"fifteen":[42],"thousand":[43],"utterances":[44],"nineteen":[46],"commands":[48,56,101],"from":[49],"two":[52],"hundred":[53],"volunteers.":[54],"The":[55,108,140,165,177],"are":[57,75,86,154],"primarily":[58],"used":[59],"applications":[61],"on":[62,88,112,132,150],"edge":[63,89],"interact":[66],"with":[67,105,135,192],"via":[69],"voice.":[70],"Models":[71],"often":[76],"much":[77],"smaller":[78],"those":[80],"speech":[82,123],"and,":[84],"thus,":[85],"preferable":[87],"devices.":[90],"then":[92],"fine-tuned":[93,166,178],"evaluated":[95],"recent":[96],"methods":[97,110],"recognizing":[99],"verifying":[103],"speakers":[104],"dataset.":[107],"selected":[109],"rely":[111],"moderately":[114],"deep":[115],"learning":[116],"model":[117,167,179],"tries":[119],"vectorize":[121],"input":[122],"signals":[124],"represented":[125],"by":[126],"spectrograms":[128],"performs":[130],"classification":[131],"the":[133,145,151],"vectors":[134],"multilayer":[137],"perceptron":[138],"network.":[139],"experimental":[141],"results":[142],"showed":[143],"models":[146],"fit":[147],"very":[148],"well":[149],"promising":[155],"applying":[157],"verification":[162,183],"Vietnamese.":[164],"achieved":[172],"an":[173],"F1-score":[174],"99%.":[176],"had":[184],"equal":[185],"error":[186],"rates":[187],"4.49%":[189],"2.27%":[191],"text-independent":[193],"text-dependent":[195],"test":[196],"sets":[197],"respectively.":[198],"Our":[199],"solution":[200],"can":[201],"applied":[203],"enhance":[205],"security":[206],"smart":[208],"interaction":[209],"systems":[210],"need":[212],"authenticate":[214],"critical":[217],"functionalities.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}