{"id":"https://openalex.org/W4415707876","doi":"https://doi.org/10.1109/tifs.2025.3626963","title":"Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-Spoofing","display_name":"Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-Spoofing","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415707876","doi":"https://doi.org/10.1109/tifs.2025.3626963"},"language":"en","primary_location":{"id":"doi:10.1109/tifs.2025.3626963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2025.3626963","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-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/A5013047791","display_name":"Tianchi Liu","orcid":"https://orcid.org/0000-0003-3472-0703"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tianchi Liu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3472-0703","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091500888","display_name":"Duc-Tuan Truong","orcid":"https://orcid.org/0009-0002-1767-7598"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Duc-Tuan Truong","raw_affiliation_strings":["Nanyang Technological University, Jurong West, Singapore","Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0009-0002-1767-7598","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029637694","display_name":"Rohan Kumar Das","orcid":"https://orcid.org/0000-0002-1332-3357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohan Kumar Das","raw_affiliation_strings":["Fortemedia Singapore, Shenton way, Singapore","Fortemedia Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-1332-3357","affiliations":[{"raw_affiliation_string":"Fortemedia Singapore, Shenton way, Singapore","institution_ids":[]},{"raw_affiliation_string":"Fortemedia Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Research Centre for Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-9133-3000","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Research Centre for Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9158-9401","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.8839,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.98737473,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"20","issue":null,"first_page":"12005","last_page":"12018"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.84170001745224,"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":0.84170001745224,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.03319999948143959,"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/T10860","display_name":"Speech and Audio Processing","score":0.015699999406933784,"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/robustness","display_name":"Robustness (evolution)","score":0.6832000017166138},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4505000114440918},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42669999599456787},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4262000024318695},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.42100000381469727},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.40400001406669617},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.37959998846054077},{"id":"https://openalex.org/keywords/nested-loop-join","display_name":"Nested loop join","score":0.36410000920295715},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.349700003862381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8716999888420105},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6832000017166138},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.42100000381469727},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39320001006126404},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38989999890327454},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.349700003862381},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33149999380111694},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C35869016","wikidata":"https://www.wikidata.org/wiki/Q846636","display_name":"Software architecture","level":3,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tifs.2025.3626963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2025.3626963","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/208220","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/208220","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4854116046","display_name":null,"funder_award_id":"ZDSYS20230626091302006","funder_id":"https://openalex.org/F4320329836","funder_display_name":"Chuzhou Science and Technology Program"},{"id":"https://openalex.org/G8135145638","display_name":null,"funder_award_id":"15210122","funder_id":"https://openalex.org/F4320333714","funder_display_name":"Cave Science and Technology Research Fund"}],"funders":[{"id":"https://openalex.org/F4320329836","display_name":"Chuzhou Science and Technology Program","ror":null},{"id":"https://openalex.org/F4320333714","display_name":"Cave Science and Technology Research Fund","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2696967604","https://openalex.org/W2752782242","https://openalex.org/W2794506738","https://openalex.org/W2928165649","https://openalex.org/W2963351448","https://openalex.org/W3024869864","https://openalex.org/W3026777299","https://openalex.org/W3034552520","https://openalex.org/W3041561163","https://openalex.org/W3095259706","https://openalex.org/W3142516134","https://openalex.org/W3197134965","https://openalex.org/W3197358873","https://openalex.org/W3198329097","https://openalex.org/W3201773091","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211424380","https://openalex.org/W3212117663","https://openalex.org/W4221154746","https://openalex.org/W4225527248","https://openalex.org/W4226264925","https://openalex.org/W4285144981","https://openalex.org/W4297841787","https://openalex.org/W4313306150","https://openalex.org/W4375869011","https://openalex.org/W4385822395","https://openalex.org/W4385822954","https://openalex.org/W4392902854","https://openalex.org/W4392903665","https://openalex.org/W4392904324","https://openalex.org/W4392908976","https://openalex.org/W4392909814","https://openalex.org/W4394744939","https://openalex.org/W4399793646","https://openalex.org/W4402111467","https://openalex.org/W4402111665","https://openalex.org/W4402111788","https://openalex.org/W4402111799","https://openalex.org/W4402111996","https://openalex.org/W4402112008","https://openalex.org/W4402112053","https://openalex.org/W4402112070","https://openalex.org/W4402112412","https://openalex.org/W4402112543","https://openalex.org/W4402351686","https://openalex.org/W4403791925","https://openalex.org/W4403955190","https://openalex.org/W4403955716","https://openalex.org/W4404125290","https://openalex.org/W4404576841","https://openalex.org/W4406138340","https://openalex.org/W4406345321","https://openalex.org/W4406461812","https://openalex.org/W4406461839","https://openalex.org/W4406461891","https://openalex.org/W4406495581","https://openalex.org/W4406803348","https://openalex.org/W4408144899","https://openalex.org/W4408354019","https://openalex.org/W4408354101","https://openalex.org/W4408354631","https://openalex.org/W4408355074","https://openalex.org/W4408355657","https://openalex.org/W4408355777"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"foundation":[1],"models":[2,159],"have":[3],"significantly":[4],"advanced":[5],"various":[6],"speech-related":[7],"tasks":[8],"by":[9],"providing":[10],"exceptional":[11],"representation":[12],"capabilities.":[13,153],"However,":[14],"their":[15],"high-dimensional":[16,73,90],"output":[17],"features":[18,74],"often":[19],"create":[20],"a":[21,38,65,98,106],"mismatch":[22],"with":[23],"downstream":[24],"task":[25],"models,":[26],"which":[27],"typically":[28],"require":[29],"lower-dimensional":[30],"inputs.":[31],"A":[32],"common":[33],"solution":[34],"is":[35],"to":[36,70],"apply":[37],"dimensionality":[39],"reduction":[40,116],"(DR)":[41],"layer,":[42],"but":[43],"this":[44],"approach":[45],"increases":[46],"parameter":[47],"overhead,":[48],"computational":[49,114],"costs,":[50],"and":[51,88,104,110,133,143,151,157],"risks":[52],"losing":[53],"valuable":[54],"information.":[55,91],"To":[56],"address":[57],"these":[58],"issues,":[59],"we":[60],"propose":[61],"Nested":[62],"Res2Net":[63],"(Nes2Net),":[64],"lightweight":[66],"back-end":[67,113],"architecture":[68],"designed":[69],"directly":[71],"process":[72],"without":[75],"DR":[76],"layers.":[77],"The":[78,154],"nested":[79],"structure":[80],"enhances":[81],"multi-scale":[82],"feature":[83,86],"extraction,":[84],"improves":[85],"interaction,":[87],"preserves":[89],"We":[92],"first":[93],"validate":[94],"Nes2Net":[95],"on":[96],"CtrSVDD,":[97],"singing":[99],"voice":[100],"deepfake":[101],"detection":[102],"dataset,":[103],"report":[105],"22%":[107],"performance":[108],"improvement":[109],"an":[111],"87%":[112],"cost":[115],"over":[117],"the":[118],"state-of-the-art":[119],"baseline.":[120],"Additionally,":[121],"extensive":[122],"testing":[123],"across":[124],"four":[125],"diverse":[126],"datasets:":[127],"ASVspoof":[128,130],"2021,":[129],"5,":[131],"PartialSpoof,":[132],"In-the-Wild,":[134],"covering":[135],"fully":[136],"spoofed":[137],"speech,":[138],"adversarial":[139],"attacks,":[140],"partial":[141],"spoofing,":[142],"real-world":[144],"scenarios,":[145],"consistently":[146],"highlights":[147],"Nes2Net\u2019s":[148],"superior":[149],"robustness":[150],"generalization":[152],"code":[155],"package":[156],"pre-trained":[158],"are":[160],"available":[161],"at":[162],"https://github.com/Liu-Tianchi/Nes2Net.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-30T00:00:00"}