{"id":"https://openalex.org/W4408354763","doi":"https://doi.org/10.1109/icassp49660.2025.10889337","title":"Integrating Spectro-Temporal Cross Aggregation and Multi-Scale Dynamic Learning for Audio Deepfake Detection","display_name":"Integrating Spectro-Temporal Cross Aggregation and Multi-Scale Dynamic Learning for Audio Deepfake Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354763","doi":"https://doi.org/10.1109/icassp49660.2025.10889337"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889337","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/A5067270756","display_name":"Yunqi Hao","orcid":"https://orcid.org/0000-0002-6838-1511"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunqi Hao","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413867","display_name":"Minqiang Xu","orcid":"https://orcid.org/0000-0003-3625-1736"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minqiang Xu","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048953421","display_name":"Yihao Chen","orcid":"https://orcid.org/0000-0002-4400-1983"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihao Chen","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100416810","display_name":"Yanyan Liu","orcid":"https://orcid.org/0000-0002-1405-7345"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyan Liu","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010540039","display_name":"Liang He","orcid":"https://orcid.org/0000-0002-4723-5486"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028800018","display_name":"Lei Fang","orcid":"https://orcid.org/0000-0002-1928-8142"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Fang","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100383252","display_name":"Lin Liu","orcid":"https://orcid.org/0000-0001-5261-650X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Liu","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]}],"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":5,"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":0.98580002784729,"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":0.98580002784729,"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":0.9617000222206116,"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":0.9589999914169312,"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":0.7878289222717285},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6294334530830383},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3545958995819092},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33656203746795654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3254845142364502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878289222717285},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6294334530830383},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3545958995819092},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33656203746795654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3254845142364502},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889337","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2799053639","https://openalex.org/W2936802426","https://openalex.org/W3034421924","https://openalex.org/W3163596559","https://openalex.org/W3197358873","https://openalex.org/W3200167423","https://openalex.org/W3201773091","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211424380","https://openalex.org/W3212117663","https://openalex.org/W3213029956","https://openalex.org/W4225331914","https://openalex.org/W4225527248","https://openalex.org/W4226013277","https://openalex.org/W4293363567","https://openalex.org/W4375869126","https://openalex.org/W4385822395","https://openalex.org/W4385822591","https://openalex.org/W4392902854","https://openalex.org/W4392903636","https://openalex.org/W4392904324","https://openalex.org/W4402112426","https://openalex.org/W6739901393","https://openalex.org/W6780218876"],"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":{"Audio":[0],"deepfake":[1,21,36],"refers":[2],"to":[3,17,39,64,109],"the":[4,50,57,91,120,133,139],"technology":[5],"of":[6,122,130],"synthesizing":[7],"speech":[8,22],"using":[9],"deep":[10],"learning":[11],"or":[12],"large":[13],"model":[14],"algorithms.":[15],"Compared":[16],"human":[18],"voice,":[19],"synthetic":[20],"exhibits":[23],"artifacts":[24,69,96],"at":[25],"global":[26,66,85],"and":[27,42,56,67,87,93],"local":[28,58,68,111],"levels,":[29],"which":[30],"can":[31],"be":[32],"leveraged":[33],"by":[34,143],"audio":[35],"detection":[37],"(ADD)":[38],"distinguish":[40],"real":[41],"fake":[43],"speech.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,126],"designed":[49],"spectro-temporal":[51],"cross":[52],"aggregation":[53],"(STCA)":[54],"module":[55,63,77,101],"multi-scale":[59,103],"dynamic":[60,104],"convolution":[61,105],"(LMDC)":[62],"extract":[65,110],"for":[70,106],"detecting":[71],"forged":[72],"information,":[73],"respectively.":[74],"The":[75,99],"STCA":[76],"utilizes":[78],"a":[79,144],"dual-branch":[80],"structure":[81],"with":[82],"cross-attention,":[83],"extracting":[84],"temporal":[86],"frequency":[88],"features":[89],"through":[90],"branches":[92],"aggregating":[94],"mutual":[95],"via":[97],"cross-attention.":[98],"LMDC":[100],"uses":[102],"grouped":[107],"features,":[108],"information.":[112],"Experimental":[113],"results":[114],"on":[115,132],"multiple":[116],"test":[117],"sets":[118],"demonstrate":[119],"effectiveness":[121],"our":[123],"method.":[124],"Specifically,":[125],"achieved":[127],"an":[128],"EER":[129],"1.87%":[131],"ASVspoof2021":[134],"DF":[135],"evaluation":[136],"set,":[137],"surpassing":[138],"current":[140],"state-of-the-art":[141],"system":[142],"relative":[145],"14.6%.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}