{"id":"https://openalex.org/W4284689653","doi":"https://doi.org/10.21437/interspeech.2022-10259","title":"Backend Ensemble for Speaker Verification and Spoofing Countermeasure","display_name":"Backend Ensemble for Speaker Verification and Spoofing Countermeasure","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4284689653","doi":"https://doi.org/10.21437/interspeech.2022-10259"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10259","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10259","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5100425399","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0001-5077-9962"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University (NPU), Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University (NPU), Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621538","display_name":"Yue Li","orcid":"https://orcid.org/0000-0001-5482-6244"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Li","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University (NPU), Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University (NPU), Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011902043","display_name":"Huan Zhao","orcid":"https://orcid.org/0000-0002-3133-3137"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Zhao","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University (NPU), Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University (NPU), Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107808955","display_name":"Qing Wang","orcid":"https://orcid.org/0009-0008-5449-4815"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University (NPU), Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University (NPU), Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066245750","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-9051-2111"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University (NPU), Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University (NPU), Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5066245750"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4381","last_page":"4385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9990000128746033,"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":0.986299991607666,"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/spoofing-attack","display_name":"Spoofing attack","score":0.7626808285713196},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7598519325256348},{"id":"https://openalex.org/keywords/countermeasure","display_name":"Countermeasure","score":0.7303178310394287},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6692261695861816},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4289964437484741},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.28061869740486145},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2701610326766968},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10232740640640259}],"concepts":[{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.7626808285713196},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598519325256348},{"id":"https://openalex.org/C21593369","wikidata":"https://www.wikidata.org/wiki/Q1032176","display_name":"Countermeasure","level":2,"score":0.7303178310394287},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6692261695861816},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4289964437484741},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.28061869740486145},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2701610326766968},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10232740640640259},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10259","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10259","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2165084404","https://openalex.org/W2170088868","https://openalex.org/W2753076865","https://openalex.org/W2784941364","https://openalex.org/W2936802426","https://openalex.org/W2972614582","https://openalex.org/W2973164265","https://openalex.org/W2979469390","https://openalex.org/W2999108204","https://openalex.org/W3011691005","https://openalex.org/W3026777299","https://openalex.org/W3041816239","https://openalex.org/W3095570773","https://openalex.org/W3104090442","https://openalex.org/W3163596559","https://openalex.org/W3177052299","https://openalex.org/W3194359420","https://openalex.org/W3197358873","https://openalex.org/W3198123200","https://openalex.org/W3201773091","https://openalex.org/W4200035372","https://openalex.org/W4205185612","https://openalex.org/W4221138880","https://openalex.org/W4226184234","https://openalex.org/W4226389478","https://openalex.org/W4243833160","https://openalex.org/W4297841768","https://openalex.org/W4309845474","https://openalex.org/W4316369887"],"related_works":["https://openalex.org/W4294437891","https://openalex.org/W4226389478","https://openalex.org/W3016138785","https://openalex.org/W4297792928","https://openalex.org/W4221161333","https://openalex.org/W3113108043","https://openalex.org/W2061278248","https://openalex.org/W2168254078","https://openalex.org/W4298202768","https://openalex.org/W1914348842"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,17,45,56,74,94,105,122,135,147,150,164,169,176],"NPU":[4],"system":[5,174],"submitted":[6],"to":[7,71,92,103,120],"Spoofing":[8],"Aware":[9],"Speaker":[10],"Verification":[11],"Challenge":[12],"2022.We":[13],"particularly":[14],"focus":[15],"on":[16,163],"backend":[18],"ensemble":[19],"for":[20,39],"speaker":[21,40,60,126],"verification":[22],"and":[23,37,42,62,128,154,161],"spoofing":[24],"countermeasure":[25,43,63,129],"from":[26],"three":[27],"aspects.Firstly,":[28],"besides":[29],"simple":[30],"concatenation,":[31],"we":[32,52,65,83,111,156],"propose":[33],"circulant":[34,50],"matrix":[35],"transformation":[36],"stacking":[38,46],"embeddings":[41,61,127],"embeddings.With":[44],"operation":[47],"of":[48,141],"newly-defined":[49],"embeddings,":[51],"almost":[53],"explore":[54],"all":[55,134],"possible":[57],"interactions":[58],"between":[59],"embeddings.Secondly,":[64],"attempt":[66],"different":[67],"convolution":[68,81,89],"neural":[69,90,118],"networks":[70,91,119],"selectively":[72],"fuse":[73],"embeddings'":[75],"salient":[76],"regions":[77],"into":[78],"channels":[79],"with":[80,168],"kernels.Finally,":[82],"design":[84],"parallel":[85],"attention":[86,114],"in":[87,97,108,115,179],"1D":[88],"learn":[93,104,121],"global":[95,123],"correlation":[96],"channel":[98],"dimensions":[99],"as":[100,102],"well":[101],"important":[106],"parts":[107],"feature":[109],"dimensions.Meanwhile,":[110],"embed":[112],"squeeze-and-excitation":[113],"2D":[116],"convolutional":[117],"dependence":[124],"among":[125],"embeddings.Experimental":[130],"results":[131],"demonstrate":[132],"that":[133],"above":[136,170],"methods":[137],"are":[138,158],"effective.After":[139],"fusion":[140],"four":[142],"well-trained":[143],"models":[144],"enhanced":[145],"by":[146],"mentioned":[148],"methods,":[149],"best":[151],"SASV-EER,":[152],"SPF-EER":[153],"SV-EER":[155],"achieve":[157],"0.559%,":[159],"0.354%":[160],"0.857%":[162],"evaluation":[165],"set":[166],"respectively.Together":[167],"contributions,":[171],"our":[172],"submission":[173],"achieves":[175],"fifth":[177],"place":[178],"this":[180],"challenge.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}