{"id":"https://openalex.org/W4392904433","doi":"https://doi.org/10.1109/icassp48485.2024.10447628","title":"GMM-ResNet2: Ensemble of Group Resnet Networks for Synthetic Speech Detection","display_name":"GMM-ResNet2: Ensemble of Group Resnet Networks for Synthetic Speech Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904433","doi":"https://doi.org/10.1109/icassp48485.2024.10447628"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.02170","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069470708","display_name":"Zhenchun Lei","orcid":"https://orcid.org/0000-0001-5846-7402"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenchun Lei","raw_affiliation_strings":["Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657114","display_name":"Hui Yan","orcid":"https://orcid.org/0009-0009-0475-433X"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Yan","raw_affiliation_strings":["Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859009","display_name":"Changhong Liu","orcid":"https://orcid.org/0000-0003-4673-5806"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhong Liu","raw_affiliation_strings":["Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016943819","display_name":"Yong Zhou","orcid":"https://orcid.org/0000-0002-4099-8077"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Zhou","raw_affiliation_strings":["Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102237368","display_name":"Minglei Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minglei Ma","raw_affiliation_strings":["Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7492,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91080986,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12101","last_page":"12105"},"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9955999851226807,"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/mixture-model","display_name":"Mixture model","score":0.8838669061660767},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6726223826408386},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6466267108917236},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6023001074790955},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5515322089195251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5418288707733154},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4956279993057251},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.482978492975235}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.8838669061660767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6726223826408386},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6466267108917236},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6023001074790955},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5515322089195251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5418288707733154},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4956279993057251},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.482978492975235},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.02170","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.02170","pdf_url":"https://arxiv.org/pdf/2407.02170","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.02170","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.02170","pdf_url":"https://arxiv.org/pdf/2407.02170","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1203572025","display_name":"\u9762\u5411\u865a\u62df\u6559\u5e08\u7684\u8bed\u97f3\u9a71\u52a8\u6559\u5b66\u52a8\u4f5c\u5e8f\u5217\u7684\u6df1\u5ea6\u751f\u6210\u6a21\u578b\u7814\u7a76","funder_award_id":"62067004","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392904433.pdf","grobid_xml":"https://content.openalex.org/works/W4392904433.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2936802426","https://openalex.org/W2967606780","https://openalex.org/W3024869864","https://openalex.org/W3041816239","https://openalex.org/W3100448777","https://openalex.org/W3142516134","https://openalex.org/W3163596559","https://openalex.org/W3197358873","https://openalex.org/W3199131409","https://openalex.org/W3199161700","https://openalex.org/W3199956586","https://openalex.org/W3200167423","https://openalex.org/W3201397251","https://openalex.org/W3201773091","https://openalex.org/W3211424380","https://openalex.org/W4212774754","https://openalex.org/W4221154745","https://openalex.org/W4226264925","https://openalex.org/W4296068766","https://openalex.org/W4296068826","https://openalex.org/W4297841773","https://openalex.org/W4297841826","https://openalex.org/W4312443924","https://openalex.org/W4372184039","https://openalex.org/W4375869011","https://openalex.org/W4385245566","https://openalex.org/W4385823280","https://openalex.org/W6810243441","https://openalex.org/W7038989634"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W1197719229","https://openalex.org/W3162054169","https://openalex.org/W2381158726","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W1516392727"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"models":[2],"are":[3,50],"widely":[4],"used":[5,51,64],"for":[6,17],"speaker":[7],"recognition":[8],"and":[9,47,82,113,149,168,173,180],"spoofing":[10],"speech":[11,19],"detection.":[12,20],"We":[13],"propose":[14],"the":[15,23,32,44,60,67,72,78,83,99,103,127,136,141,155,160,184],"GMM-ResNet2":[16,27,142,161],"synthesis":[18],"Compared":[21],"with":[22,183],"previous":[24],"GMM-ResNet":[25],"model,":[26],"has":[28],"four":[29],"improvements.":[30],"Firstly,":[31],"different":[33,37],"order":[34],"GMMs":[35,49],"have":[36],"capabilities":[38],"to":[39,43,52,65,125],"form":[40],"smooth":[41],"approximations":[42],"feature":[45],"distribution,":[46],"multiple":[48],"extract":[53],"multi-scale":[54],"Log":[55],"Gaussian":[56],"Probability":[57],"features.":[58],"Secondly,":[59],"grouping":[61],"technique":[62],"is":[63,89,106,123],"improve":[66],"classification":[68],"accuracy":[69],"by":[70,91,108],"exposing":[71],"group":[73,95],"cardinality":[74],"while":[75],"reducing":[76],"both":[77],"number":[79],"of":[80,93,131,147,152,166,171,178],"parameters":[81],"training":[84],"time.":[85],"The":[86],"final":[87],"score":[88],"obtained":[90],"ensemble":[92,133],"all":[94,132],"classifier":[96],"outputs":[97],"using":[98],"averaging":[100],"method.":[101],"Thirdly,":[102],"residual":[104],"block":[105],"improved":[107],"including":[109],"one":[110,114],"activation":[111],"function":[112,122],"batch":[115],"normalization":[116],"layer.":[117],"Finally,":[118],"an":[119,150,169],"ensemble-aware":[120],"loss":[121,129],"proposed":[124],"integrate":[126],"independent":[128],"functions":[130],"members.":[134],"On":[135,154],"ASVspoof":[137,156],"2019":[138],"LA":[139,158],"task,":[140,159],"achieves":[143,162],"a":[144,163,175],"minimum":[145,164],"t-DCF":[146,165],"0.0227":[148],"EER":[151,170],"0.79%.":[153],"2021":[157],"0.2362":[167],"2.19%,":[172],"represents":[174],"relative":[176],"reductions":[177],"31.4%":[179],"76.3%":[181],"compared":[182],"LFCC-LCNN":[185],"baseline.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}