{"id":"https://openalex.org/W4415433203","doi":"https://doi.org/10.21437/interspeech.2025-1555","title":"Generalizable Audio Spoofing Detection using Non-Semantic Representations","display_name":"Generalizable Audio Spoofing Detection using Non-Semantic Representations","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433203","doi":"https://doi.org/10.21437/interspeech.2025-1555"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1555","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1555","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.00186","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103205617","display_name":"Arnab Das","orcid":"https://orcid.org/0000-0001-9715-1435"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Arnab Das","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072129532","display_name":"Yassine El Kheir","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yassine El Kheir","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060459394","display_name":"Carlos Franzreb","orcid":"https://orcid.org/0000-0002-1188-7861"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlos Franzreb","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040023016","display_name":"Tim Herzig","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tim Herzig","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034570279","display_name":"Tim Polzehl","orcid":"https://orcid.org/0000-0001-9592-0296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tim Polzehl","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075001284","display_name":"Sebastian M\u00f6ller","orcid":"https://orcid.org/0000-0003-3057-0760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian M\u00f6ller","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103205617"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1366,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83436514,"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":"4553","last_page":"4557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9955999851226807,"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"}},"topics":[{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9955999851226807,"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/T11309","display_name":"Music and Audio Processing","score":0.9941999912261963,"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/T10860","display_name":"Speech and Audio Processing","score":0.9532999992370605,"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/generalizability-theory","display_name":"Generalizability theory","score":0.8264999985694885},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.6793000102043152},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6054999828338623},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5662999749183655},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.436599999666214},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.39070001244544983},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3862999975681305},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.362199991941452}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.8264999985694885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7915999889373779},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.6793000102043152},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6054999828338623},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5662999749183655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5580999851226807},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4657000005245209},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4074999988079071},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.39070001244544983},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3862999975681305},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2678000032901764},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.25760000944137573},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1555","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1555","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.00186","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.00186","pdf_url":"https://arxiv.org/pdf/2509.00186","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.00186","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.00186","pdf_url":"https://arxiv.org/pdf/2509.00186","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Rapid":[0],"advancements":[1],"in":[2],"generative":[3],"modeling":[4],"have":[5,66],"made":[6],"synthetic":[7],"audio":[8,62],"generation":[9],"easy,":[10],"making":[11],"speech-based":[12],"services":[13],"vulnerable":[14],"to":[15,46,69],"spoofing":[16,57],"attacks.":[17],"Consequently,":[18],"there":[19],"is":[20],"a":[21,52],"dire":[22],"need":[23],"for":[24,32,38,55],"robust":[25],"countermeasures":[26],"more":[27],"than":[28],"ever.":[29],"Existing":[30],"solutions":[31],"deepfake":[33],"detection":[34,58],"are":[35],"often":[36],"criticized":[37],"lacking":[39],"generalizability":[40],"and":[41,76,119],"fail":[42],"drastically":[43],"when":[44],"applied":[45],"real-world":[47],"data.":[48],"This":[49],"study":[50],"proposes":[51],"novel":[53],"method":[54,85],"generalizable":[56],"leveraging":[59],"non-semantic":[60,72],"universal":[61],"representations.":[63],"Extensive":[64],"experiments":[65],"been":[67],"performed":[68],"find":[70],"suitable":[71],"features":[73],"using":[74],"TRILL":[75],"TRILLsson":[77],"models.":[78],"The":[79],"results":[80],"indicate":[81],"that":[82],"the":[83,90],"proposed":[84],"achieves":[86],"comparable":[87],"performance":[88],"on":[89,99,108,114],"in-domain":[91],"test":[92,101],"set":[93],"while":[94],"significantly":[95],"outperforming":[96],"state-of-the-art":[97],"approaches":[98],"out-of-domain":[100],"sets.":[102],"Notably,":[103],"it":[104],"demonstrates":[105],"superior":[106],"generalization":[107],"public-domain":[109],"data,":[110],"surpassing":[111],"methods":[112],"based":[113],"hand-crafted":[115],"features,":[116],"semantic":[117],"embeddings,":[118],"end-to-end":[120],"architectures.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-23T00:00:00"}