{"id":"https://openalex.org/W4389474419","doi":"https://doi.org/10.1109/mmsp59012.2023.10337724","title":"Robust Deepfake Audio Detection via Bi-Level Optimization","display_name":"Robust Deepfake Audio Detection via Bi-Level Optimization","publication_year":2023,"publication_date":"2023-09-27","ids":{"openalex":"https://openalex.org/W4389474419","doi":"https://doi.org/10.1109/mmsp59012.2023.10337724"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp59012.2023.10337724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp59012.2023.10337724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"},"type":"article","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/A5100747874","display_name":"Menglu Li","orcid":"https://orcid.org/0000-0003-2441-6572"},"institutions":[{"id":"https://openalex.org/I4210092976","display_name":"Metropolitan University","ror":"https://ror.org/00ewfne71","country_code":"RS","type":"education","lineage":["https://openalex.org/I4210092976"]},{"id":"https://openalex.org/I530967","display_name":"Toronto Metropolitan University","ror":"https://ror.org/05g13zd79","country_code":"CA","type":"education","lineage":["https://openalex.org/I530967"]}],"countries":["CA","RS"],"is_corresponding":true,"raw_author_name":"Menglu Li","raw_affiliation_strings":["Toronto Metropolitan University,Faculty of Electrical and Computer Engineering,Canada","Faculty of Electrical and Computer Engineering, Toronto Metropolitan University, Canada"],"affiliations":[{"raw_affiliation_string":"Toronto Metropolitan University,Faculty of Electrical and Computer Engineering,Canada","institution_ids":["https://openalex.org/I4210092976"]},{"raw_affiliation_string":"Faculty of Electrical and Computer Engineering, Toronto Metropolitan University, Canada","institution_ids":["https://openalex.org/I530967"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021241846","display_name":"Yasaman Ahmadiadli","orcid":"https://orcid.org/0000-0003-0740-9557"},"institutions":[{"id":"https://openalex.org/I530967","display_name":"Toronto Metropolitan University","ror":"https://ror.org/05g13zd79","country_code":"CA","type":"education","lineage":["https://openalex.org/I530967"]},{"id":"https://openalex.org/I4210092976","display_name":"Metropolitan University","ror":"https://ror.org/00ewfne71","country_code":"RS","type":"education","lineage":["https://openalex.org/I4210092976"]}],"countries":["CA","RS"],"is_corresponding":false,"raw_author_name":"Yasaman Ahmadiadli","raw_affiliation_strings":["Toronto Metropolitan University,Faculty of Electrical and Computer Engineering,Canada","Faculty of Electrical and Computer Engineering, Toronto Metropolitan University, Canada"],"affiliations":[{"raw_affiliation_string":"Toronto Metropolitan University,Faculty of Electrical and Computer Engineering,Canada","institution_ids":["https://openalex.org/I4210092976"]},{"raw_affiliation_string":"Faculty of Electrical and Computer Engineering, Toronto Metropolitan University, Canada","institution_ids":["https://openalex.org/I530967"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100363146","display_name":"Xiao\u2013Ping Zhang","orcid":"https://orcid.org/0000-0001-5241-0069"},"institutions":[{"id":"https://openalex.org/I4210092976","display_name":"Metropolitan University","ror":"https://ror.org/00ewfne71","country_code":"RS","type":"education","lineage":["https://openalex.org/I4210092976"]},{"id":"https://openalex.org/I530967","display_name":"Toronto Metropolitan University","ror":"https://ror.org/05g13zd79","country_code":"CA","type":"education","lineage":["https://openalex.org/I530967"]}],"countries":["CA","RS"],"is_corresponding":false,"raw_author_name":"Xiao-Ping Zhang","raw_affiliation_strings":["Toronto Metropolitan University,Faculty of Electrical and Computer Engineering,Canada","Faculty of Electrical and Computer Engineering, Toronto Metropolitan University, Canada"],"affiliations":[{"raw_affiliation_string":"Toronto Metropolitan University,Faculty of Electrical and Computer Engineering,Canada","institution_ids":["https://openalex.org/I4210092976"]},{"raw_affiliation_string":"Faculty of Electrical and Computer Engineering, Toronto Metropolitan University, Canada","institution_ids":["https://openalex.org/I530967"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100747874"],"corresponding_institution_ids":["https://openalex.org/I4210092976","https://openalex.org/I530967"],"apc_list":null,"apc_paid":null,"fwci":1.2199,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80678475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8753585815429688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8654807806015015},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6538697481155396},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5073770880699158},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4870741665363312},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4817407429218292},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4332404136657715},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3306503891944885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06644001603126526}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8753585815429688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8654807806015015},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6538697481155396},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5073770880699158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4870741665363312},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4817407429218292},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4332404136657715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3306503891944885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06644001603126526},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp59012.2023.10337724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp59012.2023.10337724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP)","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":33,"referenced_works":["https://openalex.org/W1762936176","https://openalex.org/W2124659975","https://openalex.org/W2295634712","https://openalex.org/W2901616798","https://openalex.org/W2936802426","https://openalex.org/W2950733131","https://openalex.org/W2967606780","https://openalex.org/W2972786657","https://openalex.org/W2972811785","https://openalex.org/W2979826702","https://openalex.org/W3007151378","https://openalex.org/W3097073051","https://openalex.org/W3127781933","https://openalex.org/W3128666957","https://openalex.org/W3131786367","https://openalex.org/W3158663310","https://openalex.org/W3161011913","https://openalex.org/W3163596559","https://openalex.org/W3196974791","https://openalex.org/W3197358873","https://openalex.org/W3199161700","https://openalex.org/W3200167423","https://openalex.org/W3201397251","https://openalex.org/W3208722561","https://openalex.org/W4214896311","https://openalex.org/W4226013277","https://openalex.org/W4298394324","https://openalex.org/W4304013760","https://openalex.org/W4381198892","https://openalex.org/W6638128249","https://openalex.org/W6756859573","https://openalex.org/W6788135285","https://openalex.org/W6795208335"],"related_works":["https://openalex.org/W2366906938","https://openalex.org/W2371138613","https://openalex.org/W2349391998","https://openalex.org/W4205655149","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2000775715","https://openalex.org/W2080152487","https://openalex.org/W2239445980"],"abstract_inverted_index":{"ASVspoof":[0],"Challenges":[1],"have":[2],"been":[3],"launched":[4],"to":[5,13,16,62,83,103],"motivate":[6],"research":[7],"on":[8,27],"Deepfake":[9,30,89,111],"audio":[10,40],"detection":[11,21,60,122],"due":[12],"its":[14],"threats":[15],"society.":[17],"However,":[18],"the":[19,28,33,48,51,64,96,107,120,126,133],"state-of-the-art":[20],"models":[22],"produce":[23],"an":[24],"unsatisfactory":[25],"performance":[26],"Speech":[29],"(DF)":[31],"of":[32,50,106,109,115,135],"challenge.":[34],"The":[35,72],"DF":[36],"subset":[37],"includes":[38],"spoofed":[39],"from":[41],"various":[42],"sources,":[43],"which":[44],"can":[45],"better":[46],"reflect":[47],"robustness":[49,65],"detector.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"propose":[57],"a":[58,99,129],"novel":[59],"architecture":[61],"improve":[63],"and":[66,80,138],"generalization":[67],"ability":[68],"in":[69,125],"two":[70],"ways.":[71],"first":[73],"way":[74],"is":[75,94],"aggregating":[76],"both":[77],"learned":[78],"embeddings":[79],"hand-crafted":[81],"features":[82],"obtain":[84],"more":[85],"generalizable":[86],"representations":[87],"for":[88],"audio.":[90],"Our":[91],"second":[92],"contribution":[93],"formulating":[95],"training":[97],"process":[98],"bi-level":[100],"optimization":[101],"problem":[102],"make":[104],"use":[105],"knowledge":[108],"different":[110],"generation":[112],"methods.":[113],"Evaluations":[114],"our":[116],"proposed":[117],"method":[118],"provide":[119],"best":[121],"output":[123],"reported":[124],"literature":[127],"as":[128],"single":[130],"system":[131],"without":[132],"help":[134],"ensemble":[136],"modeling":[137],"data":[139],"augmentation.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}