{"id":"https://openalex.org/W4360992936","doi":"https://doi.org/10.1109/lsp.2023.3262419","title":"End-to-End Dual-Branch Network Towards Synthetic Speech Detection","display_name":"End-to-End Dual-Branch Network Towards Synthetic Speech Detection","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4360992936","doi":"https://doi.org/10.1109/lsp.2023.3262419"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3262419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3262419","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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/A5101646258","display_name":"Kaijie Ma","orcid":"https://orcid.org/0009-0005-6825-1935"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaijie Ma","raw_affiliation_strings":["Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science &amp; Technology, Nanjing, China","School of Computer Science, Nanjing University of Information Science &Technology, Nanjing, China","Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0005-6825-1935","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science &amp; Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Information Science &Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]},{"raw_affiliation_string":"Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107809123","display_name":"Yifan Feng","orcid":"https://orcid.org/0009-0006-9410-3036"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Feng","raw_affiliation_strings":["Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science &amp; Technology, Nanjing, China","Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing, China","School of Computer Science, Nanjing University of Information Science &Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-9410-3036","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science &amp; Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]},{"raw_affiliation_string":"Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Information Science &Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078100598","display_name":"Beijing Chen","orcid":"https://orcid.org/0000-0002-2506-0427"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beijing Chen","raw_affiliation_strings":["Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science &amp; Technology, Nanjing, China","School of Computer Science, Nanjing University of Information Science &Technology, Nanjing, China","Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2506-0427","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science &amp; Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Information Science &Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]},{"raw_affiliation_string":"Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082301986","display_name":"Guoying Zhao","orcid":"https://orcid.org/0000-0003-3694-206X"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Guoying Zhao","raw_affiliation_strings":["Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0003-3694-206X","affiliations":[{"raw_affiliation_string":"Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101646258"],"corresponding_institution_ids":["https://openalex.org/I200845125"],"apc_list":null,"apc_paid":null,"fwci":4.9156,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.96102523,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"359","last_page":"363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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/T11309","display_name":"Music and Audio Processing","score":0.9884999990463257,"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":0.8188258409500122},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6246280670166016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5781760811805725},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5586491823196411},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5290989875793457},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5175901651382446},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5004775524139404},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44733038544654846},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44643154740333557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44020509719848633},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4184330105781555},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38380753993988037},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.30912065505981445},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09759557247161865}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8188258409500122},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6246280670166016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5781760811805725},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5586491823196411},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5290989875793457},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5175901651382446},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5004775524139404},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44733038544654846},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44643154740333557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44020509719848633},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4184330105781555},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38380753993988037},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30912065505981445},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09759557247161865},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2023.3262419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3262419","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:oulu.fi:nbnfi-fe2023061555562","is_oa":false,"landing_page_url":"http://urn.fi/urn:nbn:fi-fe2023061555562","pdf_url":null,"source":{"id":"https://openalex.org/S4306400284","display_name":"University of Oulu Repository (University of Oulu)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98381234","host_organization_name":"University of Oulu","host_organization_lineage":["https://openalex.org/I98381234"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G792615751","display_name":"\u57fa\u4e8e\u6df1\u5ea6\u56db\u5143\u6570\u7f51\u7edc\u7684\u5f3a\u6cdb\u5316\u6027GAN\u751f\u6210\u4eba\u8138\u68c0\u6d4b\u7814\u7a76","funder_award_id":"62072251","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"},{"id":"https://openalex.org/F4320336704","display_name":"Infotech Oulu","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2014485509","https://openalex.org/W2123299109","https://openalex.org/W2176804518","https://openalex.org/W2295634712","https://openalex.org/W2590129515","https://openalex.org/W2745896134","https://openalex.org/W2763881998","https://openalex.org/W2936802426","https://openalex.org/W2967606780","https://openalex.org/W2972811785","https://openalex.org/W2979373447","https://openalex.org/W2990833974","https://openalex.org/W3011691005","https://openalex.org/W3015469941","https://openalex.org/W3017138616","https://openalex.org/W3024920698","https://openalex.org/W3041816239","https://openalex.org/W3100448777","https://openalex.org/W3127781933","https://openalex.org/W3132550238","https://openalex.org/W3158663310","https://openalex.org/W3160325739","https://openalex.org/W3161011913","https://openalex.org/W3163694882","https://openalex.org/W3170179936","https://openalex.org/W3197134965","https://openalex.org/W3197358873","https://openalex.org/W3198329097","https://openalex.org/W3198837656","https://openalex.org/W3200167423","https://openalex.org/W3201197228","https://openalex.org/W3209679112","https://openalex.org/W4226013277","https://openalex.org/W4285149944","https://openalex.org/W4289752563","https://openalex.org/W6639480849","https://openalex.org/W6679117816","https://openalex.org/W6791380813"],"related_works":["https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493","https://openalex.org/W2138847091","https://openalex.org/W2550171623","https://openalex.org/W596245619"],"abstract_inverted_index":{"Synthetic":[0],"speech":[1,15,29,125],"attacks":[2,42],"bring":[3],"more":[4],"threats":[5],"to":[6,22,92,111],"Automatic":[7],"Speaker":[8],"Verification":[9],"(ASV)":[10],"systems,":[11],"thus":[12],"many":[13],"synthetic":[14,28,168],"detection":[16],"(SSD)":[17],"systems":[18,34,152],"have":[19],"been":[20],"proposed":[21,147],"help":[23,112],"the":[24,37,41,73,87,108,113,116,128,137,146],"ASV":[25],"system":[26,148],"resist":[27],"attacks.":[30],"However,":[31],"existing":[32,150],"SSD":[33],"still":[35],"lack":[36],"generalization":[38,162],"ability":[39],"for":[40,86,163],"generated":[43],"by":[44],"unknown":[45,164],"synthesis":[46],"algorithms.":[47],"This":[48],"letter":[49],"proposes":[50],"an":[51,94],"end-to-end":[52],"ensemble":[53],"system,":[54],"namely":[55],"Dual-Branch":[56,109],"Network,":[57],"in":[58],"which":[59],"linear":[60],"frequency":[61],"cepstral":[62],"coefficients":[63],"(LFCC)":[64],"and":[65,99,126,156,159],"constant":[66],"Q":[67],"transform":[68],"(CQT)":[69],"are":[70,84,105],"used":[71],"as":[72],"input":[74],"of":[75,89,124,131,167],"two":[76,90],"branches":[77,91],"respectively.":[78],"In":[79],"addition,":[80],"four":[81],"fusion":[82,88],"strategies":[83],"compared":[85],"obtain":[93],"optimal":[95],"one;":[96],"multi-task":[97],"learning":[98],"convolutional":[100],"block":[101],"attention":[102],"module":[103],"(CBAM)":[104],"introduced":[106],"into":[107],"Network":[110],"network":[114],"learn":[115],"common":[117],"forgery":[118,122,165],"features":[119],"from":[120],"different":[121],"types":[123,166],"enhance":[127],"representation":[129],"power":[130],"learned":[132],"features.":[133],"Experimental":[134],"results":[135],"on":[136,153],"ASVspoof":[138],"2019":[139],"logical":[140],"access":[141],"(LA)":[142],"dataset":[143],"demonstrate":[144],"that":[145],"outperforms":[149],"state-of-the-art":[151],"both":[154],"t-DCF":[155],"EER":[157],"scores":[158],"has":[160],"good":[161],"speech.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}
