{"id":"https://openalex.org/W7117561788","doi":"https://doi.org/10.1109/jiot.2025.3649544","title":"Branch-MFA-TDNN: A Parallel Branch Speaker Verification Model for Voice IoT","display_name":"Branch-MFA-TDNN: A Parallel Branch Speaker Verification Model for Voice IoT","publication_year":2025,"publication_date":"2025-12-30","ids":{"openalex":"https://openalex.org/W7117561788","doi":"https://doi.org/10.1109/jiot.2025.3649544"},"language":null,"primary_location":{"id":"doi:10.1109/jiot.2025.3649544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3649544","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-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/A5093074693","display_name":"Guoyuan Lin","orcid":"https://orcid.org/0009-0000-5841-6365"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoyuan Lin","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-5841-6365","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121552927","display_name":"Jinbing Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinbing Deng","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-8320-5639","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121598500","display_name":"Wei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7663-278X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401173","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0003-4873-505X"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehua Wang","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032296278","display_name":"Na Xu","orcid":"https://orcid.org/0000-0003-0693-2215"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Xu","raw_affiliation_strings":["School of Mechanics and Civil Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanics and Civil Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103085687","display_name":"Fuxun Yu","orcid":"https://orcid.org/0000-0002-4880-6658"},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fei Richard Yu","raw_affiliation_strings":["School of Information Technology, Carleton University, Ottawa, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Technology, Carleton University, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I67031392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107672082","display_name":"Victor C. M. Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Victor C. M. Leung","raw_affiliation_strings":["Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, BC, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3529-2640","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74734654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"6","first_page":"11015","last_page":"11025"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8605999946594238,"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":0.8605999946594238,"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/T10863","display_name":"Voice and Speech Disorders","score":0.026399999856948853,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.018400000408291817,"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/focus","display_name":"Focus (optics)","score":0.6628000140190125},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5885000228881836},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4869000017642975},{"id":"https://openalex.org/keywords/authentication","display_name":"Authentication (law)","score":0.482699990272522},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.44200000166893005},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4239000082015991},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4203000068664551},{"id":"https://openalex.org/keywords/internet-of-things","display_name":"Internet of Things","score":0.3905999958515167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8597000241279602},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6628000140190125},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5885000228881836},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4869000017642975},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42410001158714294},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4239000082015991},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C81860439","wikidata":"https://www.wikidata.org/wiki/Q251212","display_name":"Internet of Things","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.36239999532699585},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.32850000262260437},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C527821871","wikidata":"https://www.wikidata.org/wiki/Q228502","display_name":"Access control","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C86781634","wikidata":"https://www.wikidata.org/wiki/Q2478325","display_name":"Environmental noise","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26739999651908875},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2630999982357025},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2025.3649544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3649544","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5909027457237244,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1564690036","display_name":null,"funder_award_id":"2023WLKXJ172","funder_id":"https://openalex.org/F4320323154","funder_display_name":"China University of Mining and Technology"},{"id":"https://openalex.org/G3429497752","display_name":null,"funder_award_id":"51874300","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4023559259","display_name":null,"funder_award_id":"52274160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323154","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1589137271","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2675954008","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2938358845","https://openalex.org/W3015368919","https://openalex.org/W3015598461","https://openalex.org/W3024869864","https://openalex.org/W3085051942","https://openalex.org/W3118463438","https://openalex.org/W3119931181","https://openalex.org/W3169964936","https://openalex.org/W3215290109","https://openalex.org/W4205858138","https://openalex.org/W4206908380","https://openalex.org/W4221154745","https://openalex.org/W4221154746","https://openalex.org/W4281392593","https://openalex.org/W4297841773","https://openalex.org/W4382356315","https://openalex.org/W4385245566","https://openalex.org/W4385822752","https://openalex.org/W4385823498","https://openalex.org/W4392903478","https://openalex.org/W4402112458","https://openalex.org/W4402835671"],"related_works":[],"abstract_inverted_index":{"The":[0,68],"security":[1,231],"of":[2,9,21,35,55,70,163,171],"voice":[3,43,166],"control":[4],"in":[5,38,50,75,81,114,175,205],"the":[6,16,22,31,106,115,144,148,160,169,180,189,194,211,239],"Voice":[7,36,97,226],"Internet":[8],"Things":[10],"(Voice":[11],"IoT)":[12],"heavily":[13],"relies":[14],"on":[15,30,129,193],"fast":[17],"and":[18,59,65,117,120,138,232],"accurate":[19],"authentication":[20,223],"command":[23],"issuer.":[24],"In":[25],"this":[26,51,87,199],"work,":[27],"we":[28,187],"focus":[29,128],"critical":[32],"application":[33],"scenario":[34,52],"IoT":[37,227],"underground":[39],"coal":[40],"mines,":[41],"where":[42],"commands":[44],"typically":[45,53],"last":[46],"4\u201310":[47,213],"seconds.":[48],"Speech":[49],"consists":[54],"short,":[56],"imperative":[57],"utterances":[58],"faces":[60],"challenges":[61],"from":[62],"environmental":[63,146],"noise":[64,137],"device":[66],"heterogeneity.":[67],"limitations":[69],"traditional":[71],"speaker":[72],"verification":[73,207],"models":[74,159,204],"temporal":[76,161,173],"modeling":[77],"restrict":[78],"their":[79],"performance":[80],"such":[82],"scenarios.":[83],"To":[84],"address":[85],"this,":[86],"paper":[88],"proposes":[89],"a":[90,102,184],"three-dimensional":[91],"attention":[92,113,156],"module":[93,100],"(Branch-MFA)":[94],"designed":[95],"for":[96,111,210,225,243],"IoT.":[98],"This":[99],"employs":[101],"dual-parallel":[103],"branch":[104,108],"architecture:":[105],"MFA":[107],"is":[109],"responsible":[110],"extracting":[112],"frequency":[116,131],"channel":[118],"dimensions,":[119],"its":[121,152],"multi-scale":[122],"nature":[123],"enables":[124],"it":[125],"to":[126,217],"effectively":[127],"speaker-discriminative":[130],"bands":[132],"that":[133,198,228],"remain":[134],"stable":[135],"under":[136],"different":[139],"collection":[140],"devices,":[141],"thereby":[142],"enhancing":[143],"model\u2019s":[145],"robustness;":[147],"GLTA":[149],"branch,":[150],"through":[151,183],"innovative":[153],"grouped":[154],"variable-length":[155],"mechanism,":[157],"specifically":[158],"structure":[162],"these":[164],"short":[165,176],"commands,":[167],"addressing":[168],"challenge":[170],"sparse":[172],"information":[174],"utterances.":[177],"By":[178],"integrating":[179],"dual-branch":[181],"outputs":[182],"fusion":[185],"module,":[186],"construct":[188],"Branch-MFA-TDNN":[190],"model.":[191],"Experiments":[192],"Cn-Celeb":[195],"dataset":[196],"show":[197],"model":[200],"significantly":[201],"outperforms":[202],"baseline":[203],"short-utterance":[206],"tasks,":[208],"particularly":[209],"challenging":[212],"second":[214],"duration":[215],"relevant":[216],"mine":[218],"communications,":[219],"providing":[220],"an":[221],"identity":[222],"solution":[224],"combines":[229],"high":[230],"real-time":[233],"performance.":[234],"We":[235],"have":[236],"also":[237],"released":[238],"code<sup":[240],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[241],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[242],"future":[244],"comparison.":[245]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-30T00:00:00"}
