{"id":"https://openalex.org/W7220747963","doi":"https://doi.org/10.3389/frai.2026.1928592","title":"Defending against deepfake speech attacks via feature dropout and dropin regularization in large audio language models","display_name":"Defending against deepfake speech attacks via feature dropout and dropin regularization in large audio language models","publication_year":2026,"publication_date":"2026-10-06","ids":{"openalex":"https://openalex.org/W7220747963","doi":"https://doi.org/10.3389/frai.2026.1928592","pmid":"https://pubmed.ncbi.nlm.nih.gov/42903335","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13680471"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2026.1928592","doi":"https://doi.org/10.3389/frai.2026.1928592","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2026.1928592","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2026.1928592/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2026.1928592/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126652793","display_name":"Yupei Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2802619606","display_name":"TUM Klinikum","ror":"https://ror.org/04jc43x05","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802619606","https://openalex.org/I62916508"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE","GB"],"is_corresponding":true,"raw_author_name":"Yupei Li","raw_affiliation_strings":["Chair of Health Informatics (CHI), TUM University Hospital","Group on Language, Audio, & Music (GLAM), Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Health Informatics (CHI), TUM University Hospital","institution_ids":["https://openalex.org/I2802619606","https://openalex.org/I62916508"]},{"raw_affiliation_string":"Group on Language, Audio, & Music (GLAM), Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132643003","display_name":"Yixiong Fang","orcid":"https://orcid.org/0009-0004-2483-8622","observed_orcids":["https://orcid.org/0009-0004-2483-8622"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixiong Fang","raw_affiliation_strings":["Shanghai Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140338423","display_name":"Jiahao Xue","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiahao Xue","raw_affiliation_strings":["Queen Mary University of London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037647437","display_name":"Manuel Milling","orcid":"https://orcid.org/0000-0002-8842-2958","observed_orcids":["https://orcid.org/0000-0002-8842-2958"]},"institutions":[{"id":"https://openalex.org/I2802619606","display_name":"TUM Klinikum","ror":"https://ror.org/04jc43x05","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802619606","https://openalex.org/I62916508"]},{"id":"https://openalex.org/I4403386549","display_name":"Munich Center for Machine Learning","ror":"https://ror.org/02nfy3535","country_code":"DE","type":"education","lineage":["https://openalex.org/I4403386549","https://openalex.org/I62916508","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Manuel Milling","raw_affiliation_strings":["Chair of Health Informatics (CHI), TUM University Hospital","Munich Center for Machine Learning (MCML)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Health Informatics (CHI), TUM University Hospital","institution_ids":["https://openalex.org/I2802619606","https://openalex.org/I62916508"]},{"raw_affiliation_string":"Munich Center for Machine Learning (MCML)","institution_ids":["https://openalex.org/I4403386549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130283384","display_name":"Bj\u00f6rn W. Schuller","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2802619606","display_name":"TUM Klinikum","ror":"https://ror.org/04jc43x05","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802619606","https://openalex.org/I62916508"]},{"id":"https://openalex.org/I4403386549","display_name":"Munich Center for Machine Learning","ror":"https://ror.org/02nfy3535","country_code":"DE","type":"education","lineage":["https://openalex.org/I4403386549","https://openalex.org/I62916508","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["Chair of Health Informatics (CHI), TUM University Hospital","Group on Language, Audio, & Music (GLAM), Imperial College London","Munich Center for Machine Learning (MCML)","Munich Data Science Institute (MDSI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Health Informatics (CHI), TUM University Hospital","institution_ids":["https://openalex.org/I2802619606","https://openalex.org/I62916508"]},{"raw_affiliation_string":"Group on Language, Audio, & Music (GLAM), Imperial College London","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Munich Center for Machine Learning (MCML)","institution_ids":["https://openalex.org/I4403386549"]},{"raw_affiliation_string":"Munich Data Science Institute (MDSI)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5126652793"],"corresponding_institution_ids":["https://openalex.org/I2802619606","https://openalex.org/I47508984","https://openalex.org/I62916508"],"apc_list":{"value":1950,"currency":"CHF","value_usd":2353},"apc_paid":{"value":1950,"currency":"CHF","value_usd":2353},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70099878,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"1928592","last_page":"1928592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.9970999956130981,"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":0.0007999999797903001,"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/T10860","display_name":"Speech and Audio Processing","score":0.0007999999797903001,"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/audio-deepfake-detection","display_name":"audio deepfake detection","score":0.8100000023841858},{"id":"https://openalex.org/keywords/speech-large-language-models","display_name":"speech large language models","score":0.7580000162124634},{"id":"https://openalex.org/keywords/low-rank-adapters","display_name":"low-rank adapters","score":0.6980000138282776},{"id":"https://openalex.org/keywords/ai-generated-music","display_name":"AI-generated music","score":0.6919999718666077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062000274658203},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.616599977016449},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5458999872207642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5001000165939331},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36640000343322754},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3303999900817871},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3303000032901764},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29269999265670776},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.28940001130104065},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2619999945163727}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/frai.2026.1928592","doi":"https://doi.org/10.3389/frai.2026.1928592","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2026.1928592","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2026.1928592/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13680471","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13680471/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13680471/pdf/frai-09-1928592.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Front Artif Intell","raw_type":"Text"},{"id":"pmid:42903335","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42903335","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in artificial intelligence","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:86815a61871a489ab7144e7caf73d9c7","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/86815a61871a489ab7144e7caf73d9c7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 9 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/frai.2026.1928592","doi":"https://doi.org/10.3389/frai.2026.1928592","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2026.1928592","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2026.1928592/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220747963.pdf","grobid_xml":"https://content.openalex.org/works/W7220747963.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2148154194","https://openalex.org/W2276295848","https://openalex.org/W2295634712","https://openalex.org/W2989571531","https://openalex.org/W3024869864","https://openalex.org/W3026777299","https://openalex.org/W3033711348","https://openalex.org/W3170179936","https://openalex.org/W3200167423","https://openalex.org/W3201773091","https://openalex.org/W4205858138","https://openalex.org/W4225420087","https://openalex.org/W4239510810","https://openalex.org/W4312743281","https://openalex.org/W4317181815","https://openalex.org/W4321232182","https://openalex.org/W4393379915","https://openalex.org/W4396843976","https://openalex.org/W4400188193","https://openalex.org/W4402111788","https://openalex.org/W4402112008","https://openalex.org/W4403182579","https://openalex.org/W4404211748","https://openalex.org/W4405181438","https://openalex.org/W4405182531","https://openalex.org/W4405254255","https://openalex.org/W4405899471","https://openalex.org/W4406803348","https://openalex.org/W4411832610","https://openalex.org/W4415796872","https://openalex.org/W4417216558","https://openalex.org/W7123966774","https://openalex.org/W7133358902"],"related_works":["https://openalex.org/W7114794836","https://openalex.org/W7127120701","https://openalex.org/W7163161116","https://openalex.org/W7138846099","https://openalex.org/W4392902854","https://openalex.org/W7159831908","https://openalex.org/W4415433116","https://openalex.org/W4403956249","https://openalex.org/W7164159851","https://openalex.org/W4406316742"],"abstract_inverted_index":{"Deepfakes":[0],"have":[1],"raised":[2],"widespread":[3],"concern":[4],"owing":[5],"to":[6,9,31,39,154,171,230,242],"their":[7,93],"threats":[8],"privacy,":[10],"security,":[11],"and":[12,44,78,96,113,158,193,203],"societal":[13],"trust,":[14],"driving":[15],"growing":[16],"research":[17],"interest":[18],"in":[19,134,247],"effective":[20],"detection":[21,25],"methods.":[22,224],"Audio":[23,63],"deepfake":[24,126],"has":[26],"moved":[27],"from":[28],"handcrafted-feature":[29],"classifiers":[30],"end-to-end":[32],"deep":[33],"learning":[34],"architectures":[35],"and,":[36],"more":[37],"recently,":[38],"self-supervised":[40],"speech":[41,46,55,121],"foundation":[42],"models":[43,58,90],"general-purpose":[45],"recognizers":[47],"such":[48],"as":[49,155,172,253],"Whisper.":[50],"The":[51],"use":[52],"of":[53,60,82,187,215,255],"instruction-following":[54],"large":[56,88],"language":[57,89],"(LLMs),":[59,91],"which":[61,135,250],"Speech":[62],"Language":[64],"Music":[65],"Open":[66],"Neural":[67],"Network":[68],"(SALMONN)":[69],"is":[70],"a":[71,120,130,218,243],"representative":[72],"example,":[73],"remains":[74],"comparatively":[75],"less":[76],"explored,":[77],"forms":[79],"the":[80,142,166,176,190,198,226],"setting":[81],"this":[83,104,116],"study.":[84],"We":[85],"argue":[86],"that":[87,106],"with":[92,209],"powerful":[94],"representational":[95],"information":[97],"retrieval":[98],"capabilities,":[99],"hold":[100],"significant":[101],"potential":[102],"for":[103,125],"task-provided":[105],"relevant":[107],"audio":[108,127,257],"features":[109],"are":[110],"carefully":[111],"selected":[112],"prioritized.":[114],"To":[115],"end,":[117],"we":[118,251],"employ":[119],"LLM,":[122],"specifically":[123],"SALMONN,":[124],"detection,":[128],"incorporating":[129],"two-stage":[131],"training":[132],"strategy":[133],"Stage":[136,159],"1":[137],"injects":[138],"acoustic-feature":[139],"awareness":[140],"into":[141],"Low-Rank":[143],"Adaptation":[144],"(LoRA)":[145],"adapters":[146],"via":[147],"an":[148,183,210,231],"auxiliary":[149],"feature-prediction":[150],"pretext":[151],"task":[152],"(referred":[153,170],"feature":[156,173],"dropin),":[157],"2":[160],"performs":[161],"windowed":[162],"random":[163],"retention":[164],"on":[165,189,197],"encoder":[167],"token":[168],"sequence":[169],"dropout)":[174],"before":[175],"final":[177],"real/fake":[178],"decision.":[179],"Our":[180],"approach":[181],"achieves":[182],"absolute":[184],"accuracy":[185,240],"improvement":[186,221],"0.188":[188],"FakeOrReal":[191],"benchmark":[192],"attains":[194],"state-of-the-art":[195],"performance":[196],"Automatic":[199],"Speaker":[200],"Verification":[201],"Spoofing":[202],"Countermeasures":[204],"(ASVspoof)":[205],"2019":[206],"LA":[207],"subset":[208],"Equal":[211],"Error":[212],"Rate":[213],"(EER)":[214],"0.00496,":[216],"representing":[217],"33.0%":[219],"relative":[220],"over":[222],"prior":[223,248],"Furthermore,":[225],"model":[227],"transfers":[228],"non-trivially":[229],"out-of-domain":[232],"artificial":[233],"intelligence":[234],"(AI)-generated":[235],"music":[236],"dataset":[237],"(M6),":[238],"reaching":[239],"comparable":[241],"ResNet18":[244],"baseline":[245],"reported":[246],"study,":[249],"interpret":[252],"evidence":[254],"transferable":[256],"representations":[258],"rather":[259],"than":[260],"broad":[261],"cross-domain":[262],"robustness.":[263]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-10-07T00:00:00"}