{"id":"https://openalex.org/W7117447591","doi":"https://doi.org/10.1109/jiot.2025.3648834","title":"MultiSiFer: Detecting Multiple-Speaker Fake Voice Without Speaker-Irrelative Features","display_name":"MultiSiFer: Detecting Multiple-Speaker Fake Voice Without Speaker-Irrelative Features","publication_year":2025,"publication_date":"2025-12-29","ids":{"openalex":"https://openalex.org/W7117447591","doi":"https://doi.org/10.1109/jiot.2025.3648834"},"language":null,"primary_location":{"id":"doi:10.1109/jiot.2025.3648834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3648834","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/A5121494410","display_name":"Xin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Liu","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075219529","display_name":"Xuan Hai","orcid":"https://orcid.org/0009-0002-0695-2187"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Hai","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030392751","display_name":"Ziyao Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyao Yu","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012640517","display_name":"Zihao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Zhang","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116293521","display_name":"Qingyuan Fei","orcid":null},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyuan Fei","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121465851","display_name":"Qinguo Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingguo Zhou","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I76214153"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5121494410"],"corresponding_institution_ids":["https://openalex.org/I76214153"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82160296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"7","first_page":"14084","last_page":"14095"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7678999900817871,"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":0.7678999900817871,"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":0.045499999076128006,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.01549999974668026,"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/overfitting","display_name":"Overfitting","score":0.8605999946594238},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6255999803543091},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6215000152587891},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5529000163078308},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5457000136375427},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.32820001244544983},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3278999924659729},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.32330000400543213}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8605999946594238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8535000085830688},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6255999803543091},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6215000152587891},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5763999819755554},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5529000163078308},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5457000136375427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47780001163482666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36090001463890076},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2745000123977661},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C178718744","wikidata":"https://www.wikidata.org/wiki/Q2350070","display_name":"Voice command device","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C2780589192","wikidata":"https://www.wikidata.org/wiki/Q7285140","display_name":"Raising (metalworking)","level":2,"score":0.2508000135421753},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2025.3648834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3648834","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":0.5776094794273376,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Voice":[0],"synthesis":[1],"technologies":[2],"have":[3],"advanced":[4],"rapidly,":[5],"raising":[6],"serious":[7],"concerns":[8],"about":[9],"content":[10],"security":[11],"and":[12,35,85,114],"trust.":[13],"While":[14],"many":[15],"fake":[16,49,96],"voice":[17,50,72,97],"detectors":[18],"achieve":[19],"strong":[20],"performance":[21],"in":[22,37,53,111],"controlled":[23],"settings,":[24,116],"they":[25],"often":[26],"overfit":[27],"to":[28,81],"speaker-irrelative":[29],"features":[30],"(SiFs),":[31],"exhibit":[32],"poor":[33],"robustness,":[34],"fail":[36],"multi-speaker":[38,95,115],"scenarios.":[39],"To":[40],"address":[41],"these":[42],"limitations,":[43],"we":[44],"propose":[45],"MultiSiFer,":[46],"a":[47,54,76,92],"novel":[48],"detector":[51,89],"grounded":[52],"new":[55],"design":[56],"philosophy:":[57],"rather":[58],"than":[59],"merely":[60],"distinguishing":[61],"synthetic":[62],"from":[63],"human":[64,71],"voices,":[65],"it":[66],"explicitly":[67],"prioritizes":[68],"learning":[69,84],"essential":[70],"characteristics.":[73],"MultiSiFer":[74,107],"leverages":[75],"pre-trained":[77],"speech":[78],"representation":[79],"model":[80],"enhance":[82],"this":[83],"is":[86],"the":[87],"first":[88],"trained":[90],"on":[91],"newly":[93],"curated":[94],"dataset,":[98],"enabling":[99],"effective":[100],"generalization":[101],"across":[102],"speakers.":[103],"Experiments":[104],"show":[105],"that":[106],"outperforms":[108],"existing":[109],"methods":[110],"both":[112],"standard":[113],"achieving":[117],"10.84%":[118],"average":[119],"equal":[120],"error":[121],"rate":[122],"(EER).":[123]},"counts_by_year":[],"updated_date":"2026-03-26T06:05:38.182114","created_date":"2025-12-29T00:00:00"}