{"id":"https://openalex.org/W7148379688","doi":"https://doi.org/10.1109/asru65441.2025.11434712","title":"Multilingual Dataset Integration Strategies for Robust Audio Deepfake Detection: A SAFE Challenge System","display_name":"Multilingual Dataset Integration Strategies for Robust Audio Deepfake Detection: A SAFE Challenge System","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148379688","doi":"https://doi.org/10.1109/asru65441.2025.11434712"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.01482","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100326987","display_name":"Hashim Ali","orcid":"https://orcid.org/0000-0001-6116-5616"},"institutions":[{"id":"https://openalex.org/I4210130704","display_name":"University of Michigan\u2013Dearborn","ror":"https://ror.org/035wtm547","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hashim Ali","raw_affiliation_strings":["University of Michigan,Electrical and Computer Engineering,Dearborn,USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Electrical and Computer Engineering,Dearborn,USA","institution_ids":["https://openalex.org/I4210130704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122997489","display_name":"Surya Subramani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130704","display_name":"University of Michigan\u2013Dearborn","ror":"https://ror.org/035wtm547","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Surya Subramani","raw_affiliation_strings":["University of Michigan,Electrical and Computer Engineering,Dearborn,USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Electrical and Computer Engineering,Dearborn,USA","institution_ids":["https://openalex.org/I4210130704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119711374","display_name":"Nithin Sai Adupa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130704","display_name":"University of Michigan\u2013Dearborn","ror":"https://ror.org/035wtm547","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nithin Sai Adupa","raw_affiliation_strings":["University of Michigan,Electrical and Computer Engineering,Dearborn,USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Electrical and Computer Engineering,Dearborn,USA","institution_ids":["https://openalex.org/I4210130704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119711373","display_name":"Lekha Bollinani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130704","display_name":"University of Michigan\u2013Dearborn","ror":"https://ror.org/035wtm547","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lekha Bollinani","raw_affiliation_strings":["University of Michigan,Electrical and Computer Engineering,Dearborn,USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Electrical and Computer Engineering,Dearborn,USA","institution_ids":["https://openalex.org/I4210130704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119711375","display_name":"Sali El-Loh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130704","display_name":"University of Michigan\u2013Dearborn","ror":"https://ror.org/035wtm547","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sali El-Loh","raw_affiliation_strings":["University of Michigan,Electrical and Computer Engineering,Dearborn,USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Electrical and Computer Engineering,Dearborn,USA","institution_ids":["https://openalex.org/I4210130704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132827940","display_name":"Hafiz Malik","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130704","display_name":"University of Michigan\u2013Dearborn","ror":"https://ror.org/035wtm547","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hafiz Malik","raw_affiliation_strings":["University of Michigan,Electrical and Computer Engineering,Dearborn,USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Electrical and Computer Engineering,Dearborn,USA","institution_ids":["https://openalex.org/I4210130704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100326987"],"corresponding_institution_ids":["https://openalex.org/I4210130704"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85861998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.4083000123500824,"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/T10860","display_name":"Speech and Audio Processing","score":0.4083000123500824,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.15809999406337738,"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":0.1324000060558319,"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/task","display_name":"Task (project management)","score":0.7394000291824341},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6481999754905701},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5138999819755554},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.41040000319480896},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.3522999882698059},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3312000036239624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784500002861023},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7394000291824341},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6481999754905701},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5253000259399414},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4643000066280365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4431000053882599},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.41040000319480896},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3407000005245209},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3312000036239624},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2978000044822693},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.25529998540878296}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru65441.2025.11434712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2603.01482","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.01482","pdf_url":"https://arxiv.org/pdf/2603.01482","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2603.01482","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.01482","pdf_url":"https://arxiv.org/pdf/2603.01482","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W7148379688.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2999174651","https://openalex.org/W3026777299","https://openalex.org/W3128666957","https://openalex.org/W3197358873","https://openalex.org/W3197580070","https://openalex.org/W3198858531","https://openalex.org/W3206996142","https://openalex.org/W3209984917","https://openalex.org/W3211424380","https://openalex.org/W3213029956","https://openalex.org/W4225527248","https://openalex.org/W4297841853","https://openalex.org/W4381198892","https://openalex.org/W4392903389","https://openalex.org/W4392931276","https://openalex.org/W4394862910","https://openalex.org/W4399556870","https://openalex.org/W4402111467","https://openalex.org/W4402112533","https://openalex.org/W4402351686","https://openalex.org/W4403955716","https://openalex.org/W4403956249","https://openalex.org/W4406138340","https://openalex.org/W4406461435","https://openalex.org/W4406461672","https://openalex.org/W4412945617","https://openalex.org/W4415432958"],"related_works":[],"abstract_inverted_index":{"The":[0],"SAFE":[1],"Challenge":[2],"evaluates":[3],"synthetic":[4],"speech":[5],"detection":[6],"across":[7],"three":[8,84],"tasks:":[9],"unmodified":[10],"audio,":[11],"processed":[12],"audio":[13,19,35,90,101,107],"with":[14,49,80],"compression":[15],"artifacts,":[16],"and":[17,34,63,75,88,103,112],"laundered":[18],"designed":[20],"to":[21],"evade":[22],"detection.":[23,41],"We":[24],"systematically":[25],"explore":[26],"self-supervised":[27],"learning":[28],"(SSL)":[29],"front-ends,":[30],"training":[31,85],"data":[32,86],"compositions,":[33],"length":[36],"configurations":[37],"for":[38],"robust":[39],"deepfake":[40],"Our":[42],"AASIST-based":[43],"approach":[44],"incorporates":[45],"WavLM":[46],"large":[47],"frontend":[48],"RawBoost":[50],"augmentation,":[51],"trained":[52],"on":[53],"a":[54],"multilingual":[55],"dataset":[56],"of":[57],"256,600":[58],"samples":[59],"spanning":[60],"9":[61],"languages":[62],"over":[64],"70":[65],"TTS":[66],"systems":[67],"from":[68],"Codec-Fake,":[69],"MLAAD":[70],"v5,":[71],"SpoofCeleb,":[72],"Famous":[73],"Figures,":[74],"MAILABS.":[76],"Through":[77],"extensive":[78],"experimentation":[79],"different":[81],"SSL":[82],"frontends,":[83],"versions,":[87],"two":[89],"lengths,":[91],"we":[92],"achieved":[93],"second":[94],"place":[95],"in":[96],"both":[97],"Task":[98,104],"1":[99],"(unmodified":[100],"detection)":[102],"3":[105],"(laundered":[106],"detection),":[108],"demonstrating":[109],"strong":[110],"generalization":[111],"robustness.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}