{"id":"https://openalex.org/W4408355325","doi":"https://doi.org/10.1109/icassp49660.2025.10889058","title":"CA-MHFA: A Context-Aware Multi-Head Factorized Attentive Pooling for SSL-Based Speaker Verification","display_name":"CA-MHFA: A Context-Aware Multi-Head Factorized Attentive Pooling for SSL-Based Speaker Verification","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355325","doi":"https://doi.org/10.1109/icassp49660.2025.10889058"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5111291634","display_name":"Junyi Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Junyi Peng","raw_affiliation_strings":["Brno University of Technology,Speech@FIT,Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055201620","display_name":"Ladislav Mo\u0161ner","orcid":"https://orcid.org/0000-0001-8175-2244"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ladislav Mo\u0161ner","raw_affiliation_strings":["Brno University of Technology,Speech@FIT,Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068826352","display_name":"Lin Zhang","orcid":"https://orcid.org/0000-0003-0526-9677"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lin Zhang","raw_affiliation_strings":["Brno University of Technology,Speech@FIT,Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064238041","display_name":"Old\u0159ich Plchot","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Old\u0159ich Plchot","raw_affiliation_strings":["Brno University of Technology,Speech@FIT,Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061939508","display_name":"Themos Stafylakis","orcid":"https://orcid.org/0000-0002-9227-3588"},"institutions":[{"id":"https://openalex.org/I73142707","display_name":"Athens University of Economics and Business","ror":"https://ror.org/03s262162","country_code":"GR","type":"education","lineage":["https://openalex.org/I73142707"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Themos Stafylakis","raw_affiliation_strings":["Athens University of Economics and Business,Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Athens University of Economics and Business,Greece","institution_ids":["https://openalex.org/I73142707"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Luk\u00e1\u0161 Burget","raw_affiliation_strings":["Brno University of Technology,Speech@FIT,Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan \u010cernock\u00fd","raw_affiliation_strings":["Brno University of Technology,Speech@FIT,Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9908999800682068,"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":0.9452000260353088,"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/computer-science","display_name":"Computer science","score":0.7499233484268188},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7218339443206787},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5870306491851807},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5789394378662109},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5556334853172302},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4721914529800415},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.35380661487579346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3135681748390198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7499233484268188},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7218339443206787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5870306491851807},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5789394378662109},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5556334853172302},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4721914529800415},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.35380661487579346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3135681748390198},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2969985801","https://openalex.org/W3024869864","https://openalex.org/W3026777299","https://openalex.org/W3094374485","https://openalex.org/W3197580070","https://openalex.org/W3206189675","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3212117663","https://openalex.org/W4225635674","https://openalex.org/W4319862271","https://openalex.org/W4372266902","https://openalex.org/W4372340947","https://openalex.org/W4385245566","https://openalex.org/W4385822952","https://openalex.org/W4385823373","https://openalex.org/W4391021793","https://openalex.org/W4400033122","https://openalex.org/W4402111453","https://openalex.org/W6688816777","https://openalex.org/W6780218876","https://openalex.org/W6810007534","https://openalex.org/W6857125635"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"models":[3,97,114],"for":[4],"speaker":[5],"verification":[6],"(SV)":[7],"have":[8],"gained":[9],"significant":[10],"attention":[11],"in":[12],"recent":[13],"years.":[14],"However,":[15],"existing":[16],"SSL-based":[17],"SV":[18],"systems":[19],"often":[20],"struggle":[21],"to":[22,58],"capture":[23],"local":[24],"temporal":[25],"dependencies":[26,62],"and":[27,69,87,92,103,115,120,125],"generalize":[28],"across":[29,71,111],"different":[30],"tasks.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35],"propose":[36],"context-aware":[37],"multi-head":[38],"factorized":[39],"attentive":[40],"pooling":[41],"(CA-MHFA),":[42],"a":[43],"lightweight":[44],"framework":[45],"that":[46,80],"incorporates":[47],"contextual":[48,61],"information":[49],"from":[50],"surrounding":[51],"frames.":[52],"CA-MHFA":[53,81,107],"leverages":[54],"grouped,":[55],"learnable":[56],"queries":[57],"effectively":[59],"model":[60],"while":[63],"maintaining":[64],"efficiency":[65],"by":[66],"sharing":[67],"keys":[68],"values":[70],"groups.":[72],"Experimental":[73],"results":[74],"on":[75,89],"the":[76],"VoxCeleb":[77],"dataset":[78],"show":[79],"achieves":[82],"EERs":[83],"of":[84],"0.42%,":[85],"0.48%,":[86],"0.96%":[88],"Vox1-O,":[90],"Vox1-E,":[91],"Vox1-H,":[93],"respectively,":[94],"outperforming":[95],"complex":[96],"like":[98],"WavLM-TDNN":[99],"with":[100],"fewer":[101],"parameters":[102],"faster":[104],"convergence.":[105],"Additionally,":[106],"demonstrates":[108],"strong":[109],"generalization":[110],"multiple":[112],"SSL":[113],"tasks,":[116],"including":[117],"emotion":[118],"recognition":[119],"anti-spoofing,":[121],"highlighting":[122],"its":[123],"robustness":[124],"versatility.<sup":[126],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[127],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[128]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}