{"id":"https://openalex.org/W4415707535","doi":"https://doi.org/10.1109/access.2025.3627205","title":"A Speaker Verification System Based on a Modified MLP-Mixer Student Model for Transformer Compression","display_name":"A Speaker Verification System Based on a Modified MLP-Mixer Student Model for Transformer Compression","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415707535","doi":"https://doi.org/10.1109/access.2025.3627205"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3627205","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3627205","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.2025.3627205","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046942516","display_name":"Jungwoo Heo","orcid":"https://orcid.org/0009-0008-7977-2789"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jungwoo Heo","raw_affiliation_strings":["School of Computer Science, University of Seoul, Seoul, South Korea","School of Computer Science, University of Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0008-7977-2789","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006973604","display_name":"Hyun-seo Shin","orcid":"https://orcid.org/0009-0005-6022-7674"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyun-Seo Shin","raw_affiliation_strings":["School of Computer Science, University of Seoul, Seoul, South Korea","School of Computer Science, University of Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0005-6022-7674","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036516187","display_name":"Chan-yeong Lim","orcid":"https://orcid.org/0009-0001-6671-5004"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chan-Yeong Lim","raw_affiliation_strings":["School of Computer Science, University of Seoul, Seoul, South Korea","School of Computer Science, University of Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0001-6671-5004","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113361555","display_name":"Kyo-Won Koo","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyo-Won Koo","raw_affiliation_strings":["School of Computer Science, University of Seoul, Seoul, South Korea","School of Computer Science, University of Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025074050","display_name":"Seong-Bin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-Bin Kim","raw_affiliation_strings":["School of Computer Science, University of Seoul, Seoul, South Korea","School of Computer Science, University of Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0004-7036-072X","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042447743","display_name":"Jisoo Son","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jisoo Son","raw_affiliation_strings":["School of Computer Science, University of Seoul, Seoul, South Korea","School of Computer Science, University of Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0007-2245-5945","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030475312","display_name":"Ha-Jin Yu","orcid":"https://orcid.org/0000-0003-3657-0665"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ha-Jin Yu","raw_affiliation_strings":["School of Computer Science, University of Seoul, Seoul, South Korea","School of Computer Science, University of Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-3657-0665","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I124633538"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14563072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"190371","last_page":"190378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9388999938964844,"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":0.9388999938964844,"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":0.02329999953508377,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0035000001080334187,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7483999729156494},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5760999917984009},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.47870001196861267},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.40869998931884766},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.37549999356269836},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.3095000088214874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8432000279426575},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7483999729156494},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5760999917984009},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.47870001196861267},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.42149999737739563},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.40869998931884766},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35830000042915344},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31189998984336853},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C84685590","wikidata":"https://www.wikidata.org/wiki/Q1540472","display_name":"Knowledge engineering","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26910001039505005},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3627205","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3627205","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:e3f0cda49a294cf591fc796f2dc8ba8b","is_oa":true,"landing_page_url":"https://doaj.org/article/e3f0cda49a294cf591fc796f2dc8ba8b","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 13, Pp 190371-190378 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3627205","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3627205","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/G3268536186","display_name":null,"funder_award_id":"2023R1A2C1005744","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speaker":[0],"verification":[1,152],"(SV)":[2],"systems":[3],"have":[4],"recently":[5],"achieved":[6],"remarkable":[7],"progress":[8],"through":[9],"self-supervised":[10],"learning":[11],"(SSL)":[12],"models":[13,25,73],"such":[14],"as":[15,74],"Wav2Vec2":[16],"and":[17,105,143,154],"WavLM.":[18],"Despite":[19],"their":[20,30],"strong":[21],"performance,":[22],"these":[23],"Transformer-based":[24,159],"remain":[26],"computationally":[27],"intensive,":[28],"limiting":[29],"applicability":[31],"in":[32,96,109],"mobile":[33],"or":[34],"real-time":[35],"applications.":[36],"Knowledge":[37],"distillation":[38],"has":[39],"been":[40],"employed":[41],"to":[42,77,100,113,124,158],"compress":[43],"large":[44],"SSL":[45,81],"teachers":[46],"into":[47],"lightweight":[48],"student":[49,72],"models,":[50],"yet":[51],"most":[52],"existing":[53],"approaches":[54],"retain":[55],"Transformer":[56,78],"architectures,":[57],"thereby":[58],"preserving":[59],"the":[60,90,97,110,129,147],"quadratic":[61],"cost":[62],"of":[63,89,131],"attention":[64],"mechanisms.":[65],"In":[66],"this":[67,125],"work,":[68],"we":[69],"investigate":[70],"MLP-Mixer\u2013based":[71],"an":[75],"alternative":[76],"students":[79],"for":[80,164],"knowledge":[82,119],"distillation.":[83,133],"We":[84],"propose":[85],"a":[86,106,121],"speech-oriented":[87],"redesign":[88],"MLP-Mixer":[91,127],"that":[92,146],"incorporates":[93],"1D":[94],"convolution":[95],"token-mixing":[98],"stage":[99,112],"capture":[101],"local":[102],"temporal":[103],"dependencies,":[104],"Max-Feature-Map":[107],"operation":[108],"channel-mixing":[111],"emphasize":[114],"speaker-discriminative":[115],"frequency":[116],"bands.":[117],"Distilling":[118],"from":[120],"WavLM":[122],"teacher":[123],"modified":[126],"addresses":[128],"challenges":[130],"cross-architecture":[132],"Extensive":[134],"experiments":[135],"on":[136],"diverse":[137],"benchmarks,":[138],"including":[139],"VoxCeleb,":[140],"VCMix,":[141],"VoxSRC,":[142],"VOiCES,":[144],"demonstrate":[145],"proposed":[148],"approach":[149],"achieves":[150],"superior":[151],"performance":[153],"computational":[155],"efficiency":[156],"compared":[157],"students,":[160],"highlighting":[161],"its":[162],"potential":[163],"practical":[165],"deployment.":[166]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-30T00:00:00"}