{"id":"https://openalex.org/W4394966980","doi":"https://doi.org/10.1109/taslp.2024.3389643","title":"Dual-Branch Knowledge Distillation for Noise-Robust Synthetic Speech Detection","display_name":"Dual-Branch Knowledge Distillation for Noise-Robust Synthetic Speech Detection","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394966980","doi":"https://doi.org/10.1109/taslp.2024.3389643"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3389643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3389643","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/A5037493212","display_name":"Cunhang Fan","orcid":"https://orcid.org/0000-0001-6318-8803"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cunhang Fan","raw_affiliation_strings":["Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088272481","display_name":"Mingming Ding","orcid":"https://orcid.org/0000-0001-5972-2540"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingming Ding","raw_affiliation_strings":["Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Department of Automation, Tsinghua University Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073918837","display_name":"Ruibo Fu","orcid":"https://orcid.org/0000-0001-9598-1881"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibo Fu","raw_affiliation_strings":["NLPR Lab, CASIA, Beijing, China"],"affiliations":[{"raw_affiliation_string":"NLPR Lab, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["NLPR Lab, CASIA, Beijing, China"],"affiliations":[{"raw_affiliation_string":"NLPR Lab, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["NLPR Lab, CASIA, Beijing, China"],"affiliations":[{"raw_affiliation_string":"NLPR Lab, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101578581","display_name":"Zhao Lv","orcid":"https://orcid.org/0000-0001-9727-366X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Lv","raw_affiliation_strings":["Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5037493212"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":2.8034,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91065839,"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":"2453","last_page":"2466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.7823740243911743},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6298119425773621},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5970399379730225},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4636958837509155},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.43565064668655396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4350540041923523},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4331352710723877},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3570384383201599},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3532806932926178},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08029195666313171}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7823740243911743},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6298119425773621},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5970399379730225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4636958837509155},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.43565064668655396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4350540041923523},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4331352710723877},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3570384383201599},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3532806932926178},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08029195666313171},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3389643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3389643","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/G1996838623","display_name":null,"funder_award_id":"62201002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7003438179","display_name":null,"funder_award_id":"62322120","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7853071381","display_name":null,"funder_award_id":"62101553","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":67,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W2123299109","https://openalex.org/W2159202424","https://openalex.org/W2176804518","https://openalex.org/W2289394825","https://openalex.org/W2297648422","https://openalex.org/W2473930607","https://openalex.org/W2512302098","https://openalex.org/W2603567530","https://openalex.org/W2740489634","https://openalex.org/W2745896134","https://openalex.org/W2889442120","https://openalex.org/W2936802426","https://openalex.org/W2940110727","https://openalex.org/W2963466847","https://openalex.org/W2967606780","https://openalex.org/W2970759645","https://openalex.org/W2972425344","https://openalex.org/W2990833974","https://openalex.org/W2997006708","https://openalex.org/W2998616931","https://openalex.org/W3015231328","https://openalex.org/W3015312544","https://openalex.org/W3024920698","https://openalex.org/W3034368386","https://openalex.org/W3109196171","https://openalex.org/W3138154797","https://openalex.org/W3142252347","https://openalex.org/W3161011913","https://openalex.org/W3163596559","https://openalex.org/W3170179936","https://openalex.org/W3174758275","https://openalex.org/W3177027279","https://openalex.org/W3196897556","https://openalex.org/W3197358873","https://openalex.org/W3198486673","https://openalex.org/W3198837656","https://openalex.org/W3200167423","https://openalex.org/W3200527256","https://openalex.org/W3201604899","https://openalex.org/W3201773091","https://openalex.org/W3205533980","https://openalex.org/W3206531472","https://openalex.org/W3207579445","https://openalex.org/W3212117663","https://openalex.org/W3213029956","https://openalex.org/W4221138880","https://openalex.org/W4221140371","https://openalex.org/W4221153233","https://openalex.org/W4224256913","https://openalex.org/W4224920397","https://openalex.org/W4229003981","https://openalex.org/W4297841603","https://openalex.org/W4298635730","https://openalex.org/W4312271884","https://openalex.org/W4319585984","https://openalex.org/W4372184039","https://openalex.org/W4375869126","https://openalex.org/W4375869371","https://openalex.org/W4380434618","https://openalex.org/W4381786130","https://openalex.org/W4385562590","https://openalex.org/W4385822969","https://openalex.org/W4386234565","https://openalex.org/W4388620484","https://openalex.org/W6796730497","https://openalex.org/W6799474351"],"related_works":["https://openalex.org/W2770593030","https://openalex.org/W3154990682","https://openalex.org/W2560201613","https://openalex.org/W3026162553","https://openalex.org/W2171975302","https://openalex.org/W2022352247","https://openalex.org/W2488129135","https://openalex.org/W4312219546","https://openalex.org/W2377538627","https://openalex.org/W3099502074"],"abstract_inverted_index":{"Most":[0],"research":[1],"in":[2,16,28,187,194],"synthetic":[3,42],"speech":[4,43,94,124,152],"detection":[5,44],"(SSD)":[6],"focuses":[7],"on":[8,11,177],"improving":[9],"performance":[10,26,193],"standard":[12],"noise-free":[13],"datasets.":[14],"However,":[15],"actual":[17],"situations,":[18],"noise":[19,33],"interference":[20,105],"is":[21,62,96,164,199],"usually":[22],"present,":[23],"causing":[24],"significant":[25],"degradation":[27],"SSD":[29],"systems.":[30],"To":[31],"improve":[32],"robustness,":[34],"this":[35],"paper":[36],"proposes":[37],"a":[38,48,160],"dual-branch":[39],"knowledge":[40],"distillation":[41],"(DKDSSD)":[45],"method.":[46],"Specifically,":[47],"parallel":[49],"data":[50,80,84,131],"flow":[51],"of":[52,78,106,123,133],"the":[53,58,76,83,90,104,121,130,134,141,146,182],"clean":[54,135,157],"teacher":[55],"branch":[56,61],"and":[57,64,68,86,116,126,190],"noisy":[59,79,91,117,151,188],"student":[60,92],"designed,":[63],"interactive":[65,111],"fusion":[66,112],"module":[67],"response-based":[69],"teacher-student":[70,138],"paradigms":[71],"are":[72],"proposed":[73,110,183],"to":[74,102,119,145,153,156,166],"guide":[75],"training":[77,162],"from":[81],"both":[82,168],"distribution":[85,132],"decision-making":[87],"perspectives.":[88],"In":[89],"branch,":[93],"enhancement":[95],"introduced":[97],"initially":[98],"for":[99,170],"denoising,":[100],"aiming":[101],"reduce":[103],"strong":[107],"noise.":[108],"The":[109,137],"combines":[113],"denoised":[114],"features":[115,118],"mitigate":[120],"impact":[122],"distortion":[125],"ensure":[127],"consistency":[128],"with":[129],"branch.":[136],"paradigm":[139],"maps":[140],"student's":[142],"decision":[143,148],"space":[144],"teacher's":[147],"space,":[149],"enabling":[150],"behave":[154],"similarly":[155],"speech.":[158],"Additionally,":[159],"joint":[161],"method":[163,184],"employed":[165],"optimize":[167],"branches":[169],"achieving":[171],"global":[172],"optimality.":[173],"Experimental":[174],"results":[175],"based":[176],"multiple":[178],"datasets":[179],"demonstrate":[180],"that":[181],"performs":[185],"effectively":[186],"environments":[189],"maintains":[191],"its":[192],"cross-dataset":[195],"experiments.":[196],"Source":[197],"code":[198],"available":[200],"at":[201],"<uri":[202],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[203],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/fchest/DKDSSD</uri>":[204],".":[205]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2024-04-20T00:00:00"}