{"id":"https://openalex.org/W4372184039","doi":"https://doi.org/10.1109/icassp49357.2023.10096837","title":"Learning From Yourself: A Self-Distillation Method For Fake Speech Detection","display_name":"Learning From Yourself: A Self-Distillation Method For Fake Speech Detection","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372184039","doi":"https://doi.org/10.1109/icassp49357.2023.10096837"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102858419","display_name":"Jun Xue","orcid":"https://orcid.org/0009-0001-8465-011X"},"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":"Jun Xue","raw_affiliation_strings":["Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","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":false,"raw_author_name":"Cunhang Fan","raw_affiliation_strings":["Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601","institution_ids":["https://openalex.org/I143868143"]}]},{"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":["Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367812","display_name":"Chenglong Wang","orcid":"https://orcid.org/0000-0002-4617-0182"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Chenglong Wang","raw_affiliation_strings":["Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["Qiyuan Laboratory,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qiyuan Laboratory,Beijing,China,100190","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456043","display_name":"Dan Zhang","orcid":"https://orcid.org/0000-0002-7592-3200"},"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":"Dan Zhang","raw_affiliation_strings":["Tsinghua University,Department of Psychology,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Psychology,Beijing,China,100190","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026466982","display_name":"Zhao Lv","orcid":"https://orcid.org/0000-0003-4530-4422"},"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 University,Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976999759674072,"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":0.9976999759674072,"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":0.9926999807357788,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/spectrogram","display_name":"Spectrogram","score":0.7717257738113403},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7690532803535461},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6041824817657471},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5375385880470276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.500373125076294},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48496103286743164},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.46784910559654236},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4636223614215851},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45246458053588867},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4148509204387665},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4078006148338318},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3201293349266052},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.134225994348526},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08091872930526733}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7717257738113403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7690532803535461},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6041824817657471},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5375385880470276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.500373125076294},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48496103286743164},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.46784910559654236},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4636223614215851},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45246458053588867},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4148509204387665},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4078006148338318},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3201293349266052},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.134225994348526},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08091872930526733},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":0.5600000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307500","display_name":"Youth Foundation","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326873","display_name":"National Laboratory of Pattern Recognition","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2972909277","https://openalex.org/W2987861506","https://openalex.org/W3034552520","https://openalex.org/W3127781933","https://openalex.org/W3128666957","https://openalex.org/W3131786367","https://openalex.org/W3158663310","https://openalex.org/W3158686502","https://openalex.org/W3160325739","https://openalex.org/W3161011913","https://openalex.org/W3163596559","https://openalex.org/W3196897556","https://openalex.org/W3197134965","https://openalex.org/W3198486673","https://openalex.org/W3200167423","https://openalex.org/W3201773091","https://openalex.org/W4224917447","https://openalex.org/W4297841862","https://openalex.org/W4298633873","https://openalex.org/W4298635730","https://openalex.org/W4298635755","https://openalex.org/W6768952390","https://openalex.org/W6794695087"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2016904525"],"abstract_inverted_index":{"In":[0],"this":[1,61,66],"paper,":[2],"we":[3,68],"propose":[4,69],"a":[5],"novel":[6],"self-distillation":[7],"method":[8],"for":[9,77],"fake":[10],"speech":[11],"detection":[12],"(FSD),":[13],"which":[14,44,57],"can":[15,58],"significantly":[16],"improve":[17],"the":[18,24,71,82,91,97,112,116,128,137,145,148,156],"performance":[19],"of":[20,84,133,147],"FSD":[21,85],"without":[22],"increasing":[23],"model":[25],"complexity.":[26],"For":[27],"FSD,":[28],"some":[29],"fine-grained":[30],"information":[31],"is":[32,124],"very":[33,62],"important,":[34],"such":[35],"as":[36,96],"spectrogram":[37],"defects,":[38],"mute":[39],"segments,":[40,90],"and":[41,100,120,141],"so":[42],"on,":[43],"are":[45,86],"often":[46],"perceived":[47],"by":[48,108],"shallow":[49,52,75,79,102,121],"networks.":[50,80],"However,":[51],"networks":[53,83,103],"have":[54],"much":[55],"noise,":[56],"not":[59],"capture":[60],"well.":[63],"To":[64],"address":[65],"problem,":[67],"using":[70],"deepest":[72,92,117],"network":[73,76,93,118,122],"instruct":[74],"enhancing":[78],"Specifically,":[81],"divided":[87],"into":[88],"several":[89],"being":[94],"used":[95,125],"teacher":[98],"model,":[99],"all":[101],"become":[104],"multiple":[105],"student":[106],"models":[107],"adding":[109],"classifiers.":[110],"Meanwhile,":[111],"distillation":[113],"path":[114],"between":[115],"feature":[119,129],"features":[123],"to":[126,155],"reduce":[127],"difference.":[130],"A":[131],"series":[132],"experimental":[134],"results":[135],"on":[136],"ASVspoof":[138],"2019":[139],"LA":[140],"PA":[142],"datasets":[143],"show":[144],"effectiveness":[146],"proposed":[149],"method,":[150],"with":[151],"significant":[152],"improvements":[153],"compared":[154],"baseline.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}