{"id":"https://openalex.org/W7148353839","doi":"https://doi.org/10.1109/asru65441.2025.11434806","title":"SV-Mixer: Replacing the Transformer Encoder with Lightweight MLPs for Self-Supervised Model Compresison in Speaker Verification","display_name":"SV-Mixer: Replacing the Transformer Encoder with Lightweight MLPs for Self-Supervised Model Compresison in Speaker Verification","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148353839","doi":"https://doi.org/10.1109/asru65441.2025.11434806"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132793352","display_name":"Jungwoo Heo","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"]},{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jungwoo Heo","raw_affiliation_strings":["University of Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul,Korea","institution_ids":["https://openalex.org/I124633538","https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132807030","display_name":"Hyun-Seo Shin","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"]},{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyun-Seo Shin","raw_affiliation_strings":["University of Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul,Korea","institution_ids":["https://openalex.org/I124633538","https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132801250","display_name":"Chan-Yeong Lim","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"]},{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chan-Yeong Lim","raw_affiliation_strings":["University of Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul,Korea","institution_ids":["https://openalex.org/I124633538","https://openalex.org/I197347611"]}]},{"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"]},{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyo-Won Koo","raw_affiliation_strings":["University of Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul,Korea","institution_ids":["https://openalex.org/I124633538","https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Seung-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"]},{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-Bin Kim","raw_affiliation_strings":["University of Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul,Korea","institution_ids":["https://openalex.org/I124633538","https://openalex.org/I197347611"]}]},{"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"]},{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jisoo Son","raw_affiliation_strings":["University of Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul,Korea","institution_ids":["https://openalex.org/I124633538","https://openalex.org/I197347611"]}]},{"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"]},{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ha-Jin Yu","raw_affiliation_strings":["University of Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul,Korea","institution_ids":["https://openalex.org/I124633538","https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5132793352"],"corresponding_institution_ids":["https://openalex.org/I124633538","https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":4.3637,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95467804,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9555000066757202,"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":0.9555000066757202,"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":0.009800000116229057,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.0015999999595806003,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49729999899864197},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.3747999966144562},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.3725999891757965},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3547999858856201}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6759999990463257},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49729999899864197},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4560000002384186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3937999904155731},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.3747999966144562},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25529998540878296},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2363000065088272},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22779999673366547}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2964052309","https://openalex.org/W2969985801","https://openalex.org/W3020953549","https://openalex.org/W3024388846","https://openalex.org/W3024869864","https://openalex.org/W3085139254","https://openalex.org/W3163465952","https://openalex.org/W3203140070","https://openalex.org/W3206189675","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4224821750","https://openalex.org/W4224924217","https://openalex.org/W4224933346","https://openalex.org/W4225096077","https://openalex.org/W4226046733","https://openalex.org/W4385656546","https://openalex.org/W4385823178","https://openalex.org/W4385823182","https://openalex.org/W4392902985","https://openalex.org/W4392908918","https://openalex.org/W4402111801","https://openalex.org/W4402112128","https://openalex.org/W4402112366","https://openalex.org/W4402198350","https://openalex.org/W4402704779","https://openalex.org/W4409218826","https://openalex.org/W4410351567"],"related_works":[],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"has":[3],"pushed":[4],"speaker":[5,130],"verification":[6],"accuracy":[7,120],"close":[8],"to":[9,127],"state-of-the-art":[10],"levels,":[11],"but":[12],"the":[13,37,45,107,125],"Transformer":[14,56,85],"backbones":[15],"used":[16],"in":[17],"most":[18],"SSL":[19,52,115],"encoders":[20],"hinder":[21],"on-device":[22,129],"and":[23,72,93,98],"real-time":[24],"deployment.":[25],"Prior":[26],"compression":[27],"work":[28],"trims":[29],"layer":[30],"depth":[31],"or":[32],"width":[33],"yet":[34],"still":[35],"inherits":[36],"quadratic":[38],"cost":[39],"of":[40],"self-attention.":[41],"We":[42],"propose":[43],"SV-Mixer,":[44],"first":[46],"fully":[47],"MLPbased":[48],"student":[49,86],"encoder":[50],"for":[51,63,69,76],"distillation.":[53],"SV-Mixer":[54,82],"replaces":[55],"with":[57,121],"three":[58],"lightweight":[59],"modules:":[60],"Multi-Scale":[61],"Mixing":[62,68,75],"multi-resolution":[64],"temporal":[65],"features,":[66],"Local-Global":[67],"frame-to-utterance":[70],"context,":[71],"Group":[73],"Channel":[74],"spectral":[77],"subspaces.":[78],"Distilled":[79],"from":[80],"WavLM,":[81],"outperforms":[83],"a":[84],"by":[87,95],"$14.6":[88],"\\%$":[89],"while":[90],"cutting":[91],"parameters":[92],"GMACs":[94],"over":[96],"half,":[97],"at":[99],"$\\mathbf{7":[100],"5":[101],"\\%}$":[102],"compression,":[103],"it":[104],"closely":[105],"matches":[106],"teacher\u2019s":[108],"performance.":[109],"Our":[110],"results":[111],"show":[112],"that":[113],"attention-free":[114],"students":[116],"can":[117],"deliver":[118],"teacher-level":[119],"hardwarefriendly":[122],"footprints,":[123],"opening":[124],"door":[126],"robust":[128],"verification.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}