{"id":"https://openalex.org/W7147214697","doi":"https://doi.org/10.1109/cnml68938.2026.11452384","title":"A Novel Attack-Resistant Speech Forgery Detection Method Integrating One-Class Learning and Wav2vec2","display_name":"A Novel Attack-Resistant Speech Forgery Detection Method Integrating One-Class Learning and Wav2vec2","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7147214697","doi":"https://doi.org/10.1109/cnml68938.2026.11452384"},"language":null,"primary_location":{"id":"doi:10.1109/cnml68938.2026.11452384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11452384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","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/A5102133511","display_name":"Jing Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123088","display_name":"Wuhan Technology and Business University","ror":"https://ror.org/0348f9w08","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210123088"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Yin","raw_affiliation_strings":["Wuhan Technology and Business University,College of Artificial Intelligence,Wuhan,China,430065"],"affiliations":[{"raw_affiliation_string":"Wuhan Technology and Business University,College of Artificial Intelligence,Wuhan,China,430065","institution_ids":["https://openalex.org/I4210123088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132695798","display_name":"Senyang Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123088","display_name":"Wuhan Technology and Business University","ror":"https://ror.org/0348f9w08","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210123088"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Senyang Lei","raw_affiliation_strings":["Wuhan Technology and Business University,College of Artificial Intelligence,Wuhan,China,430065"],"affiliations":[{"raw_affiliation_string":"Wuhan Technology and Business University,College of Artificial Intelligence,Wuhan,China,430065","institution_ids":["https://openalex.org/I4210123088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102133511"],"corresponding_institution_ids":["https://openalex.org/I4210123088"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93874552,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"415","last_page":"419"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7427999973297119,"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":0.7427999973297119,"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":0.041999999433755875,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.028699999675154686,"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/spoofing-attack","display_name":"Spoofing attack","score":0.8578000068664551},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6743999719619751},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.47859999537467957},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45329999923706055},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44190001487731934},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3887999951839447},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34929999709129333},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.34860000014305115}],"concepts":[{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.8578000068664551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940000295639038},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6743999719619751},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6128000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5774999856948853},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.47859999537467957},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44190001487731934},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3488999903202057},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3102000057697296},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2597000002861023}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cnml68938.2026.11452384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11452384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8134137988090515}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W4404211748","https://openalex.org/W4409605082","https://openalex.org/W4412496561","https://openalex.org/W4415827534","https://openalex.org/W4416018352","https://openalex.org/W4417073710","https://openalex.org/W4417223743","https://openalex.org/W7119161577","https://openalex.org/W7119990179"],"related_works":[],"abstract_inverted_index":{"Deep":[0,60],"learning-driven":[1],"voice":[2],"spoofing":[3,39],"techniques":[4],"pose":[5],"a":[6,37,52,73],"serious":[7],"security":[8,147],"threat":[9],"to":[10,78],"automated":[11],"speaker":[12],"verification":[13],"(ASV)":[14],"systems.":[15],"Existing":[16],"detection":[17,40,80,138],"methods":[18],"suffer":[19],"from":[20],"insufficient":[21],"generalization":[22,133],"capabilities":[23],"against":[24,148],"unknown":[25,120,149],"attacks":[26],"and":[27,71,90,116],"rely":[28],"heavily":[29],"on":[30,83,110,118],"labeled":[31],"spoof":[32],"samples.":[33],"This":[34,129],"paper":[35],"proposes":[36],"speech":[38,58,137,146],"method":[41,101],"integrating":[42],"One-Class":[43],"Learning":[44],"with":[45],"the":[46,84,99,111,119,132],"Wav2vec2":[47],"self-supervised":[48],"model.":[49],"It":[50],"constructs":[51],"hyperball":[53],"decision":[54],"boundary":[55],"for":[56,145],"authentic":[57],"using":[59],"SVDD":[61],"as":[62],"its":[63],"core,":[64],"extracts":[65],"robust":[66],"deep":[67],"features":[68],"via":[69],"Wav2vec2,":[70],"designs":[72],"multi-model":[74],"weighted":[75],"fusion":[76],"strategy":[77],"optimize":[79],"performance.":[81],"Experiments":[82],"ASVspoof":[85,91],"2019":[86],"LA":[87],"(known":[88],"attack)":[89,95],"2021":[92],"DF":[93],"(unknown":[94],"datasets":[96],"demonstrate":[97],"that":[98],"proposed":[100],"achieves":[102],"an":[103],"equal":[104],"error":[105],"rate":[106],"(EER)":[107],"of":[108],"2.13%":[109],"known":[112],"attack":[113,121],"test":[114,122],"set,":[115,123],"6.89%":[117],"significantly":[124],"outperforming":[125],"traditional":[126],"baseline":[127],"models.":[128],"effectively":[130],"addresses":[131],"challenge":[134],"in":[135],"spoofed":[136],"under":[139],"resource-constrained":[140],"scenarios,":[141],"providing":[142],"technical":[143],"support":[144],"attacks.":[150]},"counts_by_year":[],"updated_date":"2026-04-02T13:53:19.096889","created_date":"2026-04-02T00:00:00"}