{"id":"https://openalex.org/W4399618569","doi":"https://doi.org/10.1109/taslp.2024.3414340","title":"Generalizable Speech Spoofing Detection Against Silence Trimming With Data Augmentation and Multi-Task Meta-Learning","display_name":"Generalizable Speech Spoofing Detection Against Silence Trimming With Data Augmentation and Multi-Task Meta-Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399618569","doi":"https://doi.org/10.1109/taslp.2024.3414340"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3414340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3414340","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","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/A5107191669","display_name":"Li Wang","orcid":"https://orcid.org/0009-0004-7234-9145"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li Wang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089799495","display_name":"Lingyun Yu","orcid":"https://orcid.org/0000-0001-6403-761X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyun Yu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078162380","display_name":"Hongtao Xie","orcid":"https://orcid.org/0000-0002-6249-5315"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Xie","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5107191669"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":4.2052,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94901586,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"3296","last_page":"3310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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/T13289","display_name":"Infant Health and Development","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/silence","display_name":"Silence","score":0.7060526609420776},{"id":"https://openalex.org/keywords/trimming","display_name":"Trimming","score":0.6869644522666931},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.6515296101570129},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6484315395355225},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6373107433319092},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5739192962646484},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.5306465029716492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3647245168685913},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.16855895519256592},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12534436583518982},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.05873647332191467}],"concepts":[{"id":"https://openalex.org/C2781115785","wikidata":"https://www.wikidata.org/wiki/Q502261","display_name":"Silence","level":2,"score":0.7060526609420776},{"id":"https://openalex.org/C56951928","wikidata":"https://www.wikidata.org/wiki/Q3539213","display_name":"Trimming","level":2,"score":0.6869644522666931},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.6515296101570129},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6484315395355225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6373107433319092},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5739192962646484},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.5306465029716492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3647245168685913},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.16855895519256592},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12534436583518982},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.05873647332191467},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3414340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3414340","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3722848311","display_name":null,"funder_award_id":"62102127","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3828173677","display_name":null,"funder_award_id":"62121002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G472569701","display_name":null,"funder_award_id":"62032006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4897510482","display_name":null,"funder_award_id":"62232006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6288477992","display_name":null,"funder_award_id":"U23B2028","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W2123299109","https://openalex.org/W2154278880","https://openalex.org/W2294013337","https://openalex.org/W2407170210","https://openalex.org/W2590129515","https://openalex.org/W2747992279","https://openalex.org/W2799053639","https://openalex.org/W2889361425","https://openalex.org/W2900688537","https://openalex.org/W2936802426","https://openalex.org/W2962799101","https://openalex.org/W2963043696","https://openalex.org/W2963300588","https://openalex.org/W2963351448","https://openalex.org/W2963508548","https://openalex.org/W2964052309","https://openalex.org/W2967606780","https://openalex.org/W2990440871","https://openalex.org/W2992308087","https://openalex.org/W2998163473","https://openalex.org/W3024920698","https://openalex.org/W3026777299","https://openalex.org/W3035067471","https://openalex.org/W3098557217","https://openalex.org/W3110588169","https://openalex.org/W3127781933","https://openalex.org/W3158663310","https://openalex.org/W3163596559","https://openalex.org/W3170179936","https://openalex.org/W3173317327","https://openalex.org/W3196897556","https://openalex.org/W3197134965","https://openalex.org/W3198486673","https://openalex.org/W3199131409","https://openalex.org/W3200167423","https://openalex.org/W3200527256","https://openalex.org/W3201197228","https://openalex.org/W3201773091","https://openalex.org/W3207579445","https://openalex.org/W3211424380","https://openalex.org/W3212117663","https://openalex.org/W4210970267","https://openalex.org/W4221163854","https://openalex.org/W4225299853","https://openalex.org/W4225527248","https://openalex.org/W4226264925","https://openalex.org/W4294646197","https://openalex.org/W4296068826","https://openalex.org/W4297841318","https://openalex.org/W4298394377","https://openalex.org/W4313067243","https://openalex.org/W4372184039","https://openalex.org/W4372266958","https://openalex.org/W4372347465","https://openalex.org/W4381198892","https://openalex.org/W4385822614","https://openalex.org/W4385975857","https://openalex.org/W4390482908","https://openalex.org/W4392903665","https://openalex.org/W4392904324","https://openalex.org/W6631190155","https://openalex.org/W6736057607","https://openalex.org/W6745136726","https://openalex.org/W6750254146","https://openalex.org/W6760184523","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6810280618"],"related_works":["https://openalex.org/W2467235537","https://openalex.org/W4243755427","https://openalex.org/W1493074871","https://openalex.org/W2222099502","https://openalex.org/W2128287377","https://openalex.org/W1979067309","https://openalex.org/W2375590729","https://openalex.org/W2385024427","https://openalex.org/W2140535326","https://openalex.org/W2978797270"],"abstract_inverted_index":{"A":[0],"major":[1],"difficulty":[2],"in":[3,8,89,151],"speech":[4,35,116,132,161,227,231],"spoofing":[5,36,162],"detection":[6,163],"lies":[7],"improving":[9],"the":[10,25,31,43,69,82,94,124,136,156,174,191,247,262,269],"generalization":[11,32,44,157,167,193],"ability":[12,83],"to":[13,84,134,146,172,183,189,232],"detect":[14],"unknown":[15],"forgery":[16,87,149,185],"methods.":[17,186],"However,":[18],"most":[19],"previous":[20,59,112,206],"methods":[21,48,113,207],"do":[22,66],"not":[23,67],"consider":[24,210],"interference":[26,70,137],"of":[27,34,46,71,138,194],"silence":[28,52,72,76,119,128,139,266],"information":[29,267],"on":[30,75,115,142,246,261],"performance":[33,45],"detection.":[37],"Notably,":[38],"we":[39,98,121,159],"experimentally":[40],"observe":[41],"that":[42,58,208,241],"existing":[47],"drops":[49],"sharply":[50],"when":[51],"segments":[53,129,153],"are":[54],"trimmed.":[55],"This":[56],"indicates":[57],"works":[60],"have":[61],"two":[62,96],"problems:":[63],"a)":[64],"they":[65,80],"remove":[68,123],"and":[73,78,126,140,154,169,228,258,268],"over-rely":[74],"information,":[77,120],"b)":[79],"lack":[81],"uncover":[85,147],"general":[86,148],"traces":[88,150],"utterance":[90,143,152],"segments.":[91],"To":[92,108],"solve":[93],"above":[95],"problems,":[97],"propose":[99],"a":[100,165,196,225],"novel":[101,197],"Silence-Agnostic":[102],"Speech":[103],"Spoofing":[104],"Detection":[105],"(SASSD)":[106],"framework.":[107],"be":[109],"specific,":[110],"unlike":[111],"trained":[114],"samples":[117,133],"with":[118,265],"completely":[122],"leading":[125],"trailing":[127],"from":[130],"all":[131],"eliminate":[135],"focus":[141],"information.":[144],"Meanwhile,":[145],"improve":[155,190],"ability,":[158],"view":[160],"as":[164],"domain":[166,176,192],"problem":[168],"employ":[170],"meta-learning":[171],"simulate":[173],"actual":[175],"shift":[177],"scenarios,":[178],"which":[179,221],"can":[180],"reduce":[181],"overfitting":[182],"specific":[184],"In":[187,251],"addition,":[188],"meta-learning,":[195],"data":[198],"augmentation":[199,219],"method":[200,214,243,254],"named":[201],"ShuffleMix":[202],"is":[203],"proposed.":[204],"Unlike":[205],"only":[209],"inter-speech":[211],"patterns,":[212],"our":[213,242,253],"additionally":[215],"introduces":[216],"an":[217],"intra-speech":[218],"technique,":[220],"performs":[222],"enhancements":[223],"within":[224],"single":[226],"across":[229],"multiple":[230],"generate":[233],"more":[234],"diverse":[235],"forged":[236],"samples.":[237],"Extensive":[238],"experiments":[239],"show":[240],"achieves":[244,255],"SOTA":[245],"ASVspoof":[248],"2019LA":[249],"dataset.":[250],"particular,":[252],"0.231%":[256],"EER":[257,260],"2.529%":[259],"original":[263],"dataset":[264],"silence-trimmed":[270],"dataset,":[271],"respectively.":[272]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
