{"id":"https://openalex.org/W4403331453","doi":"https://doi.org/10.1109/access.2024.3479092","title":"Vietnamese Speaker Verification With Mel-Scale Filter Bank Energies and Deep Learning","display_name":"Vietnamese Speaker Verification With Mel-Scale Filter Bank Energies and Deep Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403331453","doi":"https://doi.org/10.1109/access.2024.3479092"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3479092","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3479092","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3479092","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058529922","display_name":"Thi-Thanh-Mai Nguyen","orcid":"https://orcid.org/0009-0007-9500-1135"},"institutions":[{"id":"https://openalex.org/I70349855","display_name":"Vietnam Academy of Science and Technology","ror":"https://ror.org/02wsd5p50","country_code":"VN","type":"government","lineage":["https://openalex.org/I70349855"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thi-Thanh-Mai Nguyen","raw_affiliation_strings":["Vietnam Academy of Science and Technology, Institute of Information Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0009-0007-9500-1135","affiliations":[{"raw_affiliation_string":"Vietnam Academy of Science and Technology, Institute of Information Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I70349855"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077245907","display_name":"Duc-Dung Nguyen","orcid":"https://orcid.org/0000-0001-9867-0106"},"institutions":[{"id":"https://openalex.org/I70349855","display_name":"Vietnam Academy of Science and Technology","ror":"https://ror.org/02wsd5p50","country_code":"VN","type":"government","lineage":["https://openalex.org/I70349855"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Duc-Dung Nguyen","raw_affiliation_strings":["Vietnam Academy of Science and Technology, Institute of Information Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vietnam Academy of Science and Technology, Institute of Information Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I70349855"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026818330","display_name":"Chi-Mai Luong","orcid":null},"institutions":[{"id":"https://openalex.org/I70349855","display_name":"Vietnam Academy of Science and Technology","ror":"https://ror.org/02wsd5p50","country_code":"VN","type":"government","lineage":["https://openalex.org/I70349855"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Chi-Mai Luong","raw_affiliation_strings":["Vietnam Academy of Science and Technology, Institute of Information Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vietnam Academy of Science and Technology, Institute of Information Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I70349855"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.6109,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7445432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"12","issue":null,"first_page":"150114","last_page":"150122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9959999918937683,"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":0.9959999918937683,"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":0.995199978351593,"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":0.9488000273704529,"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":0.7577852010726929},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.7205933332443237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7059293985366821},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7011914253234863},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6440399289131165},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5586107969284058},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4510549306869507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44616830348968506},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.40164172649383545},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08396050333976746},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07689791917800903}],"concepts":[{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.7577852010726929},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.7205933332443237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7059293985366821},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7011914253234863},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6440399289131165},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5586107969284058},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4510549306869507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44616830348968506},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.40164172649383545},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08396050333976746},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07689791917800903},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3479092","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3479092","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f4a1721b710849798b3f1432cd9a571a","is_oa":true,"landing_page_url":"https://doaj.org/article/f4a1721b710849798b3f1432cd9a571a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 150114-150122 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3479092","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3479092","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4288788110","display_name":null,"funder_award_id":"NCVCC02.03/24-24","funder_id":"https://openalex.org/F4320313223","funder_display_name":"Vietnam Academy of Science and Technology"},{"id":"https://openalex.org/G8892237275","display_name":null,"funder_award_id":"VAST01.08/23-24","funder_id":"https://openalex.org/F4320313223","funder_display_name":"Vietnam Academy of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320313223","display_name":"Vietnam Academy of Science and Technology","ror":"https://ror.org/02wsd5p50"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W105311456","https://openalex.org/W195252322","https://openalex.org/W309418507","https://openalex.org/W1224261078","https://openalex.org/W1590424750","https://openalex.org/W2002094307","https://openalex.org/W2018342351","https://openalex.org/W2041823554","https://openalex.org/W2059857061","https://openalex.org/W2062826588","https://openalex.org/W2064675550","https://openalex.org/W2107638917","https://openalex.org/W2114925438","https://openalex.org/W2141401351","https://openalex.org/W2148154194","https://openalex.org/W2150769028","https://openalex.org/W2187089797","https://openalex.org/W2239141610","https://openalex.org/W2279516409","https://openalex.org/W2289384004","https://openalex.org/W2465080433","https://openalex.org/W2620629206","https://openalex.org/W2747165665","https://openalex.org/W2748488820","https://openalex.org/W2752782242","https://openalex.org/W2772958598","https://openalex.org/W2794506738","https://openalex.org/W2798765714","https://openalex.org/W2808631503","https://openalex.org/W2916104401","https://openalex.org/W2950635152","https://openalex.org/W2963026686","https://openalex.org/W2974062151","https://openalex.org/W2976594877","https://openalex.org/W2981087920","https://openalex.org/W3010925296","https://openalex.org/W3013020904","https://openalex.org/W3024869864","https://openalex.org/W3163361649","https://openalex.org/W3206886023","https://openalex.org/W4210849719","https://openalex.org/W4239510810","https://openalex.org/W4285112472","https://openalex.org/W4312321798","https://openalex.org/W4313178214","https://openalex.org/W4385245566","https://openalex.org/W4385823030","https://openalex.org/W4391021709","https://openalex.org/W6681192965"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W204267554","https://openalex.org/W2186375278","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"Mel-Frequency":[0],"Cepstral":[1],"Coefficients":[2],"(MFCCs)":[3],"have":[4],"been":[5],"extensively":[6],"used":[7],"as":[8],"input":[9],"for":[10,109],"many":[11],"traditional":[12],"and":[13,53,98,100,175,188],"modern":[14],"speech":[15,28,79],"processing":[16,80],"systems.":[17],"The":[18,157],"power":[19],"of":[20,27,33,39,44,57,70,130,151],"MFCCs":[21,146],"lies":[22],"in":[23,77,147],"the":[24,35,40,45,50,54,67,71,90,142,149,163,172,181],"compact":[25,128],"representation":[26,124],"signals,":[29],"which":[30,73],"is":[31],"capable":[32],"capturing":[34],"essential":[36],"phonetic":[37],"content":[38],"speech.":[41],"However,":[42],"most":[43],"MFCC":[46,59],"energy":[47],"concentrates":[48],"on":[49,134,162,180],"low-order":[51],"coefficients,":[52,72],"flat":[55],"distribution":[56,129],"high-order":[58],"values":[60],"makes":[61],"convolutional":[62],"operators":[63],"less":[64],"sensitive":[65],"to":[66],"transient":[68],"details":[69],"may":[74],"be":[75],"important":[76],"certain":[78],"tasks":[81],"like":[82],"speaker":[83,113,123,137],"recognition.":[84],"In":[85],"this":[86],"paper,":[87],"we":[88,101],"analyze":[89],"differences":[91],"between":[92],"Mel-scale":[93],"filter":[94],"bank":[95],"energies":[96],"(MFBEs)":[97],"MFCCs,":[99],"show":[102,140],"that":[103,141],"MFBEs":[104,115,143],"are":[105],"more":[106,127],"effective":[107],"inputs":[108],"deep":[110,117,154],"learning-based":[111],"Vietnamese":[112,136],"verification.":[114],"help":[116],"learning":[118,155],"models":[119],"learn":[120],"a":[121,126],"better":[122],"with":[125,171,185],"embedding":[131],"vectors.":[132],"Experiments":[133],"two":[135],"verification":[138],"datasets":[139],"consistently":[144],"outperform":[145],"improving":[148],"performance":[150],"some":[152],"state-of-the-art":[153],"models.":[156],"equal":[158],"error":[159],"rate":[160],"(EER)":[161],"Vietnam-Celeb":[164],"test":[165,183],"dataset":[166,184],"was":[167],"reduced":[168],"by":[169],"1.14%":[170],"ResNetSE-34":[173],"model":[174,187],"2.36%,":[176],"or":[177],"51.6%":[178],"improvement,":[179],"VLSP2021":[182],"ECAPA-TDNN":[186],"transfer":[189],"learning.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
