{"id":"https://openalex.org/W7148482104","doi":"https://doi.org/10.1109/asru65441.2025.11434594","title":"Rapidly Adapting to New Voice Spoofing: Few-Shot Detection of Synthesized Speech Under Distribution Shifts","display_name":"Rapidly Adapting to New Voice Spoofing: Few-Shot Detection of Synthesized Speech Under Distribution Shifts","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148482104","doi":"https://doi.org/10.1109/asru65441.2025.11434594"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434594","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":["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/A5109715082","display_name":"Ashi Garg","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ashi Garg","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076833848","display_name":"Zexin Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zexin Cai","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024403590","display_name":"Henry Li Xinyuan","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henry Li Xinyuan","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leibny Paola Garc\u00eda-Perera","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132818424","display_name":"Kevin Duh Sanjeev Khudanpur","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Duh Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132804747","display_name":"Matthew Wiesner","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Wiesner","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111560316","display_name":"Nicholas Andrews","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Andrews","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5109715082"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87358985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8809000253677368,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8809000253677368,"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/T10863","display_name":"Voice and Speech Disorders","score":0.04479999840259552,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.015799999237060547,"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/reduction","display_name":"Reduction (mathematics)","score":0.5590999722480774},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.5213000178337097},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4934999942779541},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.48649999499320984},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.421099990606308},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37130001187324524},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.35350000858306885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7213000059127808},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.652400016784668},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5590999722480774},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.5213000178337097},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4934999942779541},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.48649999499320984},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4205999970436096},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2775999903678894},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434594","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1897996326","https://openalex.org/W1994116808","https://openalex.org/W2403139431","https://openalex.org/W2407170210","https://openalex.org/W2602814339","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2937579788","https://openalex.org/W2963539064","https://openalex.org/W2990833974","https://openalex.org/W3026777299","https://openalex.org/W3096197423","https://openalex.org/W3198429080","https://openalex.org/W4225527248","https://openalex.org/W4294831657","https://openalex.org/W4297841787","https://openalex.org/W4381198892","https://openalex.org/W4385245566","https://openalex.org/W4392909950","https://openalex.org/W4393156644","https://openalex.org/W4401652690","https://openalex.org/W4402116004","https://openalex.org/W4403680773","https://openalex.org/W4406461482","https://openalex.org/W4408354450","https://openalex.org/W4415797692"],"related_works":[],"abstract_inverted_index":{"We":[0,46],"address":[1],"the":[2,21,39,65,72,93],"challenge":[3],"of":[4,41,67],"detecting":[5],"synthesized":[6],"speech":[7],"under":[8],"distribution":[9,33,82,90],"shifts\u2014arising":[10],"from":[11],"unseen":[12],"synthesis":[13],"methods,":[14],"speakers,":[15],"languages,":[16],"or":[17],"audio":[18],"conditions\u2014relative":[19],"to":[20,31,52,80],"training":[22,78],"data.":[23],"Fewshot":[24],"learning":[25],"methods":[26],"are":[27],"a":[28,42,48],"promising":[29],"way":[30],"tackle":[32],"shifts":[34,83,91],"by":[35],"rapidly":[36],"adapting":[37],"on":[38,117,126],"basis":[40],"few":[43,106],"in-distribution":[44,110],"samples.":[45],"propose":[47],"self-attentive":[49],"prototypical":[50],"network":[51],"enable":[53],"more":[54],"robust":[55],"fewshot":[56,74],"adaptation.":[57],"To":[58],"evaluate":[59],"our":[60,96],"approach,":[61],"we":[62],"systematically":[63],"compare":[64],"performance":[66],"traditional":[68],"zero-shot":[69,94],"detectors":[70],"and":[71,122],"proposed":[73,97],"detectors,":[75],"carefully":[76],"controlling":[77],"conditions":[79,88],"introduce":[81],"at":[84],"evaluation":[85],"time.":[86],"In":[87],"where":[89],"hamper":[92],"performance,":[95],"few-shot":[98],"adaptation":[99],"technique":[100],"can":[101],"quickly":[102],"adapt":[103],"using":[104],"as":[105,107],"$\\mathbf{1":[108],"0}$":[109],"samples\u2014achieving":[111],"upto":[112],"32%":[113],"relative":[114,124],"EER":[115],"reduction":[116,125],"deepfakes":[118],"in":[119],"Japanese":[120],"language":[121],"20%":[123],"ASVspoof":[127],"2021":[128],"Deepfake":[129],"dataset.":[130]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-03T00:00:00"}