{"id":"https://openalex.org/W4392902824","doi":"https://doi.org/10.1109/icassp48485.2024.10447245","title":"Score Calibration Based on Consistency Measure Factor for Speaker Verification","display_name":"Score Calibration Based on Consistency Measure Factor for Speaker Verification","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902824","doi":"https://doi.org/10.1109/icassp48485.2024.10447245"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447245","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":["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/A5110371198","display_name":"Yu Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yu Zheng","raw_affiliation_strings":["Unisound AI Technology Co., Ltd.,Beijing,China","Unisound AI Technology Co., Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443330","display_name":"Yajun Zhang","orcid":"https://orcid.org/0000-0002-9661-6349"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yajun Zhang","raw_affiliation_strings":["Unisound AI Technology Co., Ltd.,Beijing,China","Unisound AI Technology Co., Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061918821","display_name":"Chuanying Niu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuanying Niu","raw_affiliation_strings":["Unisound AI Technology Co., Ltd.,Beijing,China","Unisound AI Technology Co., Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021274571","display_name":"Yibin Zhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yibin Zhan","raw_affiliation_strings":["Unisound AI Technology Co., Ltd.,Beijing,China","Unisound AI Technology Co., Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056415893","display_name":"Yanhua Long","orcid":"https://orcid.org/0000-0003-0924-408X"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhua Long","raw_affiliation_strings":["Shanghai Normal University,SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction,Shanghai,China","SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Normal University,SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction,Shanghai,China","institution_ids":["https://openalex.org/I21945476"]},{"raw_affiliation_string":"SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042316448","display_name":"Dongxing Xu","orcid":"https://orcid.org/0000-0001-7445-1398"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongxing Xu","raw_affiliation_strings":["Unisound AI Technology Co., Ltd.,Beijing,China","Unisound AI Technology Co., Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5110371198"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61642821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"12371","last_page":"12375"},"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":0.9994000196456909,"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/speaker-verification","display_name":"Speaker verification","score":0.7636022567749023},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7506620287895203},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7161668539047241},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.6739169359207153},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6632153987884521},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6242573261260986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5161905884742737},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.5088768005371094},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4651558995246887},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4392234683036804},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3480718731880188},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32089924812316895},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21469736099243164},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1654638648033142}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7636022567749023},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7506620287895203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7161668539047241},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6739169359207153},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6632153987884521},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6242573261260986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5161905884742737},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.5088768005371094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4651558995246887},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4392234683036804},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3480718731880188},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32089924812316895},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21469736099243164},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1654638648033142},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447245","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2122364000","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2747165665","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2962898354","https://openalex.org/W2969985801","https://openalex.org/W3013020904","https://openalex.org/W3024869864","https://openalex.org/W3094374485","https://openalex.org/W3103152812","https://openalex.org/W3109225549","https://openalex.org/W3167976421","https://openalex.org/W3198698812","https://openalex.org/W3205310163","https://openalex.org/W4296972891","https://openalex.org/W4306867198","https://openalex.org/W4386185131","https://openalex.org/W6688816777","https://openalex.org/W6769178842","https://openalex.org/W6801723603","https://openalex.org/W6843237292","https://openalex.org/W6855969671"],"related_works":["https://openalex.org/W1968216131","https://openalex.org/W2355011896","https://openalex.org/W3089964815","https://openalex.org/W1581134722","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W2169890399","https://openalex.org/W2170952763","https://openalex.org/W2359348847","https://openalex.org/W2148960477"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,14,60,120],"new":[4],"scoring":[5,101],"calibration":[6,111],"method":[7,72,96,115],"named":[8],"\"Consistency-Aware":[9],"Score":[10],"Calibration\",":[11],"which":[12],"introduces":[13],"Consistency":[15],"Measure":[16],"Factor":[17],"(CMF)":[18],"to":[19,51,62,85],"measure":[20],"the":[21,37,43,53,67,71,74,94,124,133,139],"stability":[22],"of":[23,76,138],"audio":[24,69],"voiceprints":[25],"in":[26,39,119,136],"similarity":[27,54],"scores":[28,64],"for":[29,123],"speaker":[30,126],"verification.":[31],"The":[32,113],"CMF":[33,58,95],"is":[34,97],"inspired":[35],"by":[36],"limitations":[38],"segment":[40,100],"scoring,":[41],"where":[42,130],"segments":[44],"with":[45,83,107],"shorter":[46],"length":[47],"are":[48],"not":[49],"friendly":[50],"calculate":[52],"score.":[55],"By":[56],"using":[57],"as":[59],"scale":[61],"calibrate":[63],"calculated":[65],"on":[66],"whole":[68],"length,":[70],"improves":[73],"performance":[75],"different":[77],"state-of-the-art":[78],"systems":[79],"significantly,":[80],"including":[81],"ResNet":[82],"34":[84],"518":[86],"layers":[87],"and":[88,102],"RepVGG.":[89],"Experimental":[90],"results":[91],"show":[92],"that":[93],"better":[98],"than":[99],"shows":[103],"excellent":[104],"complementary":[105],"information":[106],"other":[108],"normalization":[109],"or":[110],"methods.":[112],"proposed":[114,118],"was":[116],"first":[117],"system":[121],"description":[122],"VoxCeleb":[125],"recognition":[127],"challenge":[128],"2023,":[129],"it":[131],"achieved":[132],"1st":[134],"place":[135],"Track1":[137],"challenge.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}