{"id":"https://openalex.org/W4408354101","doi":"https://doi.org/10.1109/icassp49660.2025.10888328","title":"Generalizable Audio Deepfake Detection via Latent Space Refinement and Augmentation","display_name":"Generalizable Audio Deepfake Detection via Latent Space Refinement and Augmentation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354101","doi":"https://doi.org/10.1109/icassp49660.2025.10888328"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888328","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/A5004675212","display_name":"Wen Huang","orcid":"https://orcid.org/0000-0001-7682-4354"},"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":"Wen Huang","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005181515","display_name":"Ying-Qiu Gu","orcid":"https://orcid.org/0000-0001-9225-9084"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanmei Gu","raw_affiliation_strings":["Ant Group,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group,Shanghai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049694267","display_name":"Zhiming Wang","orcid":"https://orcid.org/0000-0002-4854-2170"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiming Wang","raw_affiliation_strings":["Ant Group,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group,Shanghai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110390049","display_name":"Huijia Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huijia Zhu","raw_affiliation_strings":["Ant Group,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group,Shanghai,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"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":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"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/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9891999959945679,"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":0.9785000085830688,"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":0.7923822402954102},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4967535138130188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36701899766921997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7923822402954102},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4967535138130188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36701899766921997},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888328","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":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2902453469","https://openalex.org/W2936774411","https://openalex.org/W2969985801","https://openalex.org/W3026777299","https://openalex.org/W3127781933","https://openalex.org/W3197358873","https://openalex.org/W3201773091","https://openalex.org/W3209984917","https://openalex.org/W3211424380","https://openalex.org/W3213029956","https://openalex.org/W4225527248","https://openalex.org/W4225854381","https://openalex.org/W4297841787","https://openalex.org/W4307823382","https://openalex.org/W4372266958","https://openalex.org/W4392902854","https://openalex.org/W4392902878","https://openalex.org/W4392903665","https://openalex.org/W4392904324","https://openalex.org/W4392910562","https://openalex.org/W4402111467","https://openalex.org/W4402111655","https://openalex.org/W4402111788","https://openalex.org/W4402111996","https://openalex.org/W4402112426","https://openalex.org/W4402112476","https://openalex.org/W4402716253","https://openalex.org/W4404609248","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Advances":[0],"in":[1,92],"speech":[2,16],"synthesis":[3],"technologies,":[4],"like":[5],"text-to-speech":[6],"(TTS)":[7],"and":[8,46,122,124,131,136],"voice":[9],"conversion":[10],"(VC),":[11],"have":[12],"made":[13],"detecting":[14],"deepfake":[15,56],"increasingly":[17],"challenging.":[18],"Spoofing":[19],"countermeasures":[20],"often":[21],"struggle":[22],"to":[23,51,72,99],"generalize":[24],"effectively,":[25],"particularly":[26],"when":[27],"faced":[28],"with":[29],"unseen":[30],"attacks.":[31],"To":[32],"address":[33],"this,":[34],"we":[35],"propose":[36],"a":[37,101],"novel":[38],"strategy":[39],"that":[40,129],"integrates":[41],"Latent":[42,47],"Space":[43,48],"Refinement":[44],"(LSR)":[45],"Augmentation":[49],"(LSA)":[50],"improve":[52],"the":[53,65,69,75,93,97],"generalization":[54],"of":[55,104],"detection":[57],"systems.":[58],"LSR":[59,130],"introduces":[60],"multiple":[61],"learnable":[62],"prototypes":[63],"for":[64],"spoof":[66],"class,":[67],"refining":[68],"latent":[70,94],"space":[71],"better":[73],"capture":[74],"intricate":[76],"variations":[77],"within":[78],"spoofed":[79,84],"data.":[80],"LSA":[81,132],"further":[82],"diversifies":[83],"data":[85],"representations":[86],"by":[87],"applying":[88],"augmentation":[89],"techniques":[90],"directly":[91],"space,":[95],"enabling":[96],"model":[98],"learn":[100],"broader":[102],"range":[103],"spoofing":[105],"patterns.":[106],"We":[107],"evaluated":[108],"our":[109],"approach":[110],"on":[111],"four":[112],"representative":[113],"datasets,":[114],"i.e.":[115],"ASVspoof":[116,119],"2019":[117],"LA,":[118],"2021":[120],"LA":[121],"DF,":[123],"In-The-Wild.":[125],"The":[126],"results":[127],"show":[128],"perform":[133],"well":[134],"individually,":[135],"their":[137],"integration":[138],"achieves":[139],"competitive":[140],"results,":[141],"matching":[142],"or":[143],"surpassing":[144],"current":[145],"state-of-the-art":[146],"methods.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}