{"id":"https://openalex.org/W4392902960","doi":"https://doi.org/10.1109/icassp48485.2024.10447606","title":"SR-HuBERT : An Efficient Pre-Trained Model for Speaker Verification","display_name":"SR-HuBERT : An Efficient Pre-Trained Model for Speaker Verification","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902960","doi":"https://doi.org/10.1109/icassp48485.2024.10447606"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447606","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/A5112932714","display_name":"Yishuang Li","orcid":"https://orcid.org/0009-0003-3466-0701"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]},{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yishuang Li","raw_affiliation_strings":["Xiamen University,Institute of Artificial Intelligence,China","School of Electronic Science and Engineering, Xiamen University, China","Institute of Artificial Intelligence, Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Institute of Artificial Intelligence,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109692702","display_name":"Hukai Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hukai Huang","raw_affiliation_strings":["Xiamen University,School of Informatics,China","School of Informatics, Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057983137","display_name":"Zhicong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]},{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicong Chen","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,China","School of Electronic Science and Engineering, Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310824","display_name":"Wenhao Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Guan","raw_affiliation_strings":["Xiamen University,School of Informatics,China","School of Informatics, Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111094266","display_name":"Jiayan Lin","orcid":"https://orcid.org/0000-0002-0305-2784"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayan Lin","raw_affiliation_strings":["Xiamen University,School of Informatics,China","School of Informatics, Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412926","display_name":"Lin Li","orcid":"https://orcid.org/0000-0003-0426-6546"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Xiamen University,Institute of Artificial Intelligence,China","School of Electronic Science and Engineering, Xiamen University, China","Institute of Artificial Intelligence, Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Institute of Artificial Intelligence,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":["Xiamen University,School of Informatics,China","School of Informatics, Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5112932714"],"corresponding_institution_ids":["https://openalex.org/I191208505","https://openalex.org/I75867142"],"apc_list":null,"apc_paid":null,"fwci":1.8253,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86393206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11591","last_page":"11595"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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/T10028","display_name":"Topic Modeling","score":0.9911999702453613,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8341120481491089},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6745966672897339},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6076443195343018},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5992998480796814},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5901046395301819},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5751210451126099},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5417801141738892},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4991276264190674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4928460121154785},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4847797751426697},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4821564555168152},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.47583842277526855},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43541571497917175},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4211139976978302},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3906463086605072},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3477817177772522},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.16297733783721924},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07461431622505188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8341120481491089},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6745966672897339},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6076443195343018},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5992998480796814},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5901046395301819},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5751210451126099},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5417801141738892},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4991276264190674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4928460121154785},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4847797751426697},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4821564555168152},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.47583842277526855},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43541571497917175},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4211139976978302},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3906463086605072},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3477817177772522},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.16297733783721924},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07461431622505188},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447606","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2164998314","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2752782242","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2933138175","https://openalex.org/W2964054038","https://openalex.org/W2973049979","https://openalex.org/W3010925296","https://openalex.org/W3024869864","https://openalex.org/W3036601975","https://openalex.org/W3163421828","https://openalex.org/W3197580070","https://openalex.org/W3198275944","https://openalex.org/W3206189675","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221161148","https://openalex.org/W4224934182","https://openalex.org/W4225096077","https://openalex.org/W4296068420","https://openalex.org/W4372260593","https://openalex.org/W6780218876","https://openalex.org/W6810007534"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Recently,":[0],"pre-trained":[1],"models":[2,38],"(PTMs)":[3],"have":[4],"been":[5],"extensively":[6],"applied":[7],"in":[8,57,104],"speaker":[9,39,75],"verification":[10],"(SV)":[11],"and":[12,77],"greatly":[13],"boosted":[14],"system":[15],"performance.":[16],"However,":[17],"mainstream":[18],"PTMs":[19,116],"currently":[20],"concentrate":[21],"on":[22,70,92,117,125],"using":[23],"frame-level":[24],"universal":[25,59],"representations.":[26,60],"In":[27],"this":[28],"paper,":[29],"we":[30],"propose":[31],"a":[32,86],"novel":[33],"pre-training":[34,88],"framework":[35,49],"that":[36],"jointly":[37],"information":[40,55],"\u2014":[41],"Speaker":[42],"Related":[43],"HuBERT,":[44],"abbreviated":[45],"as":[46],"SR-HuBERT.":[47,102],"This":[48],"aims":[50],"to":[51,73],"further":[52],"explore":[53],"speaker-related":[54,83,126],"inherent":[56],"speech":[58],"The":[61],"proposed":[62,101],"SR-HuBERT":[63,111,121],"utilizes":[64],"an":[65],"unsupervised":[66],"clustering":[67],"algorithm":[68],"based":[69],"graph":[71],"structures":[72],"generate":[74],"pseudo-labels":[76],"promotes":[78],"the":[79,97,100,105,113],"learning":[80],"of":[81,99,107,128],"segment-level":[82],"representations":[84],"through":[85],"multi-task":[87],"framework.":[89],"Experimental":[90],"results":[91],"VoxCeleb1":[93],"test":[94],"set":[95],"demonstrate":[96],"effectiveness":[98],"Even":[103],"scenarios":[106],"limited":[108],"fine-tuning":[109],"data,":[110],"outperforms":[112],"other":[114],"existing":[115],"SV":[118],"tasks.":[119],"Additionally,":[120],"also":[122],"performs":[123],"well":[124],"tasks":[127],"SUPERB":[129],"benchmark.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}