{"id":"https://openalex.org/W7148371483","doi":"https://doi.org/10.1109/asru65441.2025.11434759","title":"Token-based Attractors and Cross-attention in Spoof Diarization","display_name":"Token-based Attractors and Cross-attention in Spoof Diarization","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148371483","doi":"https://doi.org/10.1109/asru65441.2025.11434759"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434759","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/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":true,"raw_author_name":"Kyo-Won Koo","raw_affiliation_strings":["University of Seoul,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul,Seoul,Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132824306","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"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chan-Yeong Lim","raw_affiliation_strings":["University of Seoul,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul,Seoul,Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132819246","display_name":"Jee-Weon Jun","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":"Jee-Weon Jun","raw_affiliation_strings":["University of Seoul,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul,Seoul,Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132800744","display_name":"Hye-jin Shim","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hye-Jin Shim","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"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":["University of Seoul,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul,Seoul,Korea","institution_ids":["https://openalex.org/I124633538"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113361555"],"corresponding_institution_ids":["https://openalex.org/I124633538"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74978173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.40059998631477356,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.40059998631477356,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.2969000041484833,"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/T11448","display_name":"Face recognition and analysis","score":0.15320000052452087,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/spoofing-attack","display_name":"Spoofing attack","score":0.8860999941825867},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7412999868392944},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5077000260353088},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.36629998683929443},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3596000075340271},{"id":"https://openalex.org/keywords/attractor","display_name":"Attractor","score":0.3400999903678894}],"concepts":[{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.8860999941825867},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7412999868392944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7084000110626221},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5077000260353088},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44190001487731934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4401000142097473},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C164380108","wikidata":"https://www.wikidata.org/wiki/Q507187","display_name":"Attractor","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434759","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.774193286895752}],"awards":[],"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":28,"referenced_works":["https://openalex.org/W2176804518","https://openalex.org/W2745896134","https://openalex.org/W2974328324","https://openalex.org/W3095212884","https://openalex.org/W3163596559","https://openalex.org/W3196774886","https://openalex.org/W3201773091","https://openalex.org/W4221138880","https://openalex.org/W4224920249","https://openalex.org/W4225661121","https://openalex.org/W4296069292","https://openalex.org/W4312891570","https://openalex.org/W4313306150","https://openalex.org/W4323896824","https://openalex.org/W4385822749","https://openalex.org/W4391020683","https://openalex.org/W4391021454","https://openalex.org/W4391892525","https://openalex.org/W4392903271","https://openalex.org/W4392903644","https://openalex.org/W4402111498","https://openalex.org/W4402111665","https://openalex.org/W4402112367","https://openalex.org/W4402112476","https://openalex.org/W4408354019","https://openalex.org/W4408354631","https://openalex.org/W4408354763","https://openalex.org/W7133228923"],"related_works":[],"abstract_inverted_index":{"Spoof":[0],"diarization":[1],"identifies":[2],"\u201cwhat":[3],"spoofed":[4,13,91],"when\u201d":[5],"in":[6,123],"a":[7,21,30],"given":[8],"speech":[9],"by":[10],"temporally":[11],"locating":[12],"regions":[14],"and":[15,35,58,68,90,107,127],"determining":[16],"their":[17],"manipulation":[18],"techniques.":[19],"As":[20],"first":[22],"step":[23],"toward":[24],"this":[25],"task,":[26],"prior":[27],"work":[28],"proposed":[29],"two-branch":[31],"model":[32],"for":[33,43,63],"localization":[34],"spoof":[36,44],"type":[37],"clustering,":[38],"which":[39],"laid":[40],"the":[41,51],"foundation":[42],"diarization.":[45],"However,":[46],"its":[47],"simple":[48],"structure":[49],"limits":[50],"ability":[52],"to":[53,99],"capture":[54],"complex":[55],"spoofing":[56,70,128],"patterns":[57],"lacks":[59],"explicit":[60],"reference":[61],"points":[62],"distinguishing":[64],"between":[65,105],"bona":[66,88,124],"fide":[67,89,125],"various":[69],"types.":[71],"To":[72],"address":[73],"these":[74],"limitations,":[75],"our":[76,118],"approach":[77,119],"introduces":[78],"learnable":[79],"tokens":[80],"where":[81],"each":[82],"token":[83],"represents":[84],"acoustic":[85],"features":[86],"of":[87],"speech.":[92,109],"These":[93],"attractors":[94],"interact":[95],"with":[96],"frame-level":[97],"embeddings":[98],"extract":[100],"discriminative":[101],"representations,":[102],"improving":[103],"separation":[104],"genuine":[106],"generated":[108],"Vast":[110],"experiments":[111],"on":[112],"PartialSpoof":[113],"dataset":[114],"consistently":[115],"demon-strate":[116],"that":[117],"outperforms":[120],"existing":[121],"methods":[122],"detection":[126],"method":[129],"clustering.":[130]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-03T00:00:00"}