{"id":"https://openalex.org/W4416799932","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249209","title":"Variational Regularization for End-to-End Speech Deepfake Detection","display_name":"Variational Regularization for End-to-End Speech Deepfake Detection","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799932","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249209"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5066338559","display_name":"Siqing Qin","orcid":"https://orcid.org/0009-0002-0786-4859"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Siqing Qin","raw_affiliation_strings":["The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,Hong Kong SAR,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,Hong Kong SAR,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,Hong Kong SAR,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,Hong Kong SAR,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,Hong Kong SAR,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,Hong Kong SAR,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004094196","display_name":"Pasquale Lisena","orcid":"https://orcid.org/0000-0003-3094-5585"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pasquale Lisena","raw_affiliation_strings":["EURECOM,Sophia Antipolis,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EURECOM,Sophia Antipolis,France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049594655","display_name":"Massimiliano Todisco","orcid":"https://orcid.org/0000-0003-2883-0324"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Massimiliano Todisco","raw_affiliation_strings":["EURECOM,Sophia Antipolis,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EURECOM,Sophia Antipolis,France","institution_ids":["https://openalex.org/I1902872"]}]}],"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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2241","last_page":"2246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2913999855518341,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2913999855518341,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.2207999974489212,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.05009999871253967,"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/autoencoder","display_name":"Autoencoder","score":0.7476999759674072},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6829000115394592},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6572999954223633},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.574999988079071},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48420000076293945},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.47290000319480896},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4708999991416931},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4456999897956848}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7476999759674072},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6829000115394592},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6572999954223633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5940999984741211},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.574999988079071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5613999962806702},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.47290000319480896},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4708999991416931},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4456999897956848},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34459999203681946},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3237999975681305},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C27753989","wikidata":"https://www.wikidata.org/wiki/Q284885","display_name":"Superposition principle","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2953000068664551},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C64618476","wikidata":"https://www.wikidata.org/wiki/Q164296","display_name":"Variational method","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:fr.eurecom:8514","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196942","display_name":"Graduate School and Research Center in Digital Science (EURECOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1902872","host_organization_name":"EURECOM","host_organization_lineage":["https://openalex.org/I1902872"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"APSIPA 2025, 17th Asia Pacific Signal and Information Processing Association Annual Summit and Conference, 22-24 October 2025, Shangri-la, Singapore","raw_type":"Conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2799053639","https://openalex.org/W2972956697","https://openalex.org/W3015301038","https://openalex.org/W3038083940","https://openalex.org/W3128666957","https://openalex.org/W3163596559","https://openalex.org/W3197358873","https://openalex.org/W3201773091","https://openalex.org/W4224927738","https://openalex.org/W4225527248","https://openalex.org/W4312827992","https://openalex.org/W4372184039","https://openalex.org/W4375869126","https://openalex.org/W4382935290","https://openalex.org/W4385822660","https://openalex.org/W4386832555","https://openalex.org/W4387665604","https://openalex.org/W4392902854","https://openalex.org/W4400926002","https://openalex.org/W4402112008","https://openalex.org/W4403955261","https://openalex.org/W4403955716","https://openalex.org/W4405181438","https://openalex.org/W4408353245","https://openalex.org/W4408353669"],"related_works":[],"abstract_inverted_index":{"Current":[0],"research":[1],"in":[2,41],"end-to-end":[3],"speech":[4],"deepfake":[5,74],"detection":[6],"predominantly":[7],"centers":[8],"around":[9],"inputting":[10],"\u201craw\u201d":[11],"waveforms":[12,30,37],"to":[13,26,77,95],"a":[14,53,59,73,79],"deep":[15,23],"architecture,":[16],"such":[17],"as":[18],"RawNet2,":[19],"and":[20,105,121],"training":[21],"the":[22,29,42,90,100],"neural":[24],"network":[25],"predict":[27],"if":[28],"are":[31],"fake.":[32],"However,":[33],"direct":[34],"processing":[35],"of":[36,102],"could":[38],"cause":[39],"over-parameterization":[40],"network,":[43],"reducing":[44],"its":[45],"generalizability.":[46],"To":[47],"overcome":[48],"this":[49],"limitation,":[50],"we":[51,68],"propose":[52],"multi-level":[54],"variational":[55,92],"regularization":[56,93],"framework":[57],"integrating":[58],"modified":[60],"Variational":[61],"Autoencoder":[62],"(VAE)":[63],"with":[64,72],"discriminative":[65],"constraints.":[66],"Specifically,":[67],"adopt":[69],"an":[70],"VAE":[71],"discrimination":[75],"constraint":[76],"regularize":[78],"RawNet2-based":[80],"high-level":[81],"feature":[82],"map":[83],"(HFM)":[84],"extractor.":[85],"Experimental":[86],"results":[87],"show":[88],"that":[89,98],"proposed":[91],"leads":[94],"HFM":[96],"features":[97],"improve":[99],"performance":[101],"AASIST,":[103],"SE-Rawformer,":[104],"RawBMamba":[106],"by":[107],"<tex":[108,122],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[109,123],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\text{3":[110],"6.":[111],"0":[112,118],"1":[113],"\\%,":[114],"}":[115],"\\text{1":[116],"0.":[117],"7":[119],"\\%}$</tex>,":[120,127],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\text{6.":[124],"3":[125],"5":[126],"respectively.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}