{"id":"https://openalex.org/W3010845645","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023158","title":"Replay detection using CQT-based modified group delay feature and ResNeWt network in ASVspoof 2019","display_name":"Replay detection using CQT-based modified group delay feature and ResNeWt network in ASVspoof 2019","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3010845645","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023158","mag":"3010845645"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5089344893","display_name":"Xingliang Cheng","orcid":"https://orcid.org/0000-0002-1955-3970"},"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":"Xingliang Cheng","raw_affiliation_strings":["Department of Computer Science and Technology, Center for Speech and Language Technologies, Research Institute of Information Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Center for Speech and Language Technologies, Research Institute of Information Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111983309","display_name":"Mingxing Xu","orcid":"https://orcid.org/0009-0000-3878-315X"},"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":"Mingxing Xu","raw_affiliation_strings":["Department of Computer Science and Technology, Center for Speech and Language Technologies, Research Institute of Information Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Center for Speech and Language Technologies, Research Institute of Information Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"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":"Thomas Fang Zheng","raw_affiliation_strings":["Department of Computer Science and Technology, Center for Speech and Language Technologies, Research Institute of Information Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Center for Speech and Language Technologies, Research Institute of Information Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"540","last_page":"545"},"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":0.9995999932289124,"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":0.996399998664856,"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":0.7989375591278076},{"id":"https://openalex.org/keywords/replay-attack","display_name":"Replay attack","score":0.7505872249603271},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.6715927720069885},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6533770561218262},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6238977313041687},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5945330858230591},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5428419709205627},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5001077651977539},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49686887860298157},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48935240507125854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4736313223838806},{"id":"https://openalex.org/keywords/authentication","display_name":"Authentication (law)","score":0.09812697768211365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989375591278076},{"id":"https://openalex.org/C11560541","wikidata":"https://www.wikidata.org/wiki/Q1756025","display_name":"Replay attack","level":3,"score":0.7505872249603271},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.6715927720069885},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6533770561218262},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6238977313041687},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5945330858230591},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5428419709205627},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5001077651977539},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49686887860298157},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48935240507125854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4736313223838806},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.09812697768211365},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1550888325","https://openalex.org/W1638038541","https://openalex.org/W2072473772","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2549139847","https://openalex.org/W2588445447","https://openalex.org/W2590129515","https://openalex.org/W2607084024","https://openalex.org/W2747024632","https://openalex.org/W2747182415","https://openalex.org/W2747419477","https://openalex.org/W2747872086","https://openalex.org/W2789949544","https://openalex.org/W2799053639","https://openalex.org/W2888980597","https://openalex.org/W2889361425","https://openalex.org/W2922258480","https://openalex.org/W2936802426","https://openalex.org/W2963907370","https://openalex.org/W6684191040","https://openalex.org/W6743510496"],"related_works":["https://openalex.org/W2547760228","https://openalex.org/W2794664665","https://openalex.org/W3007059209","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W4220832730","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W1688416049","https://openalex.org/W3173366380"],"abstract_inverted_index":{"Automatic":[0],"Speaker":[1],"Verification":[2],"(ASV)":[3],"technology":[4],"is":[5,25,42,180,187,194],"vulnerable":[6],"to":[7,27,34,95,196],"various":[8],"kinds":[9],"of":[10,55,99],"spoofing":[11],"attacks,":[12,48],"including":[13],"speech":[14],"synthesis,":[15],"voice":[16],"conversion,":[17],"and":[18,59,87,122,138,148,158,185,203],"replay.":[19],"Among":[20],"them,":[21],"the":[22,46,53,61,65,74,85,97,116,120,129,170,176,178,197],"replay":[23,47,111],"attack":[24],"easy":[26],"implement,":[28],"posing":[29],"a":[30,104],"more":[31],"severe":[32],"threat":[33],"ASV.":[35],"The":[36,125],"constant-Q":[37,56],"cepstrum":[38],"coefficient":[39],"(CQCC)":[40],"feature":[41,133],"effective":[43],"for":[44,110],"detecting":[45],"but":[49],"it":[50],"only":[51],"utilizes":[52],"magnitude":[54],"transform":[57],"(CQT)":[58],"discards":[60],"phase":[62,98],"information.":[63],"Meanwhile,":[64],"commonly":[66],"used":[67],"Gaussian":[68],"mixture":[69],"model":[70,73,115],"(GMM)":[71],"cannot":[72],"reverberation":[75],"present":[76,103],"in":[77,93,119],"far-field":[78],"recordings.":[79],"In":[80],"this":[81],"paper,":[82],"we":[83,102],"incorporate":[84],"CQT":[86],"modified":[88],"group":[89],"delay":[90],"function":[91],"(MGD)":[92],"order":[94],"utilize":[96],"CQT.":[100],"Also,":[101],"simple":[105],"2D-convolution":[106],"multi-branch":[107],"network":[108],"architecture":[109],"detection,":[112],"which":[113],"can":[114,140],"distortion":[117],"both":[118,146],"time":[121],"frequency":[123],"domains.":[124],"experiment":[126],"shows":[127],"that":[128],"proposed":[130],"CQT-based":[131],"MGD":[132,136],"outperforms":[134],"traditional":[135],"feature,":[137],"performance":[139],"be":[141],"further":[142],"improved":[143],"by":[144,175,183,190],"combining":[145],"magnitude-based":[147],"phase-based":[149],"feature.":[150],"Our":[151,192],"best":[152],"fusion":[153],"system":[154,173,193],"achieves":[155],"0.0096":[156],"min-tDCF":[157,179],"0.39%":[159],"EER":[160,186],"on":[161],"ASVspoof":[162,198],"2019":[163,199],"Physical":[164,200],"Access":[165,201],"evaluation":[166],"set.":[167],"Comparing":[168],"with":[169],"CQCC-GMM":[171],"baseline":[172],"provided":[174],"organizer,":[177],"relatively":[181,188],"reduced":[182,189],"96.09%":[184],"96.46%.":[191],"submitted":[195],"sub-challenge":[202],"won":[204],"1st":[205],"place.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}