{"id":"https://openalex.org/W4402979088","doi":"https://doi.org/10.1109/icme57554.2024.10687367","title":"Speaker Recognition Based on Pre-Trained Model and Deep Clustering","display_name":"Speaker Recognition Based on Pre-Trained Model and Deep Clustering","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979088","doi":"https://doi.org/10.1109/icme57554.2024.10687367"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5010540039","display_name":"Liang He","orcid":"https://orcid.org/0000-0002-4723-5486"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020817636","display_name":"Zhida Song","orcid":"https://orcid.org/0000-0002-4987-5962"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhida Song","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089332230","display_name":"Shuanghong Liu","orcid":"https://orcid.org/0009-0007-8597-2229"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuanghong Liu","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060654795","display_name":"Mengqi Niu","orcid":"https://orcid.org/0000-0003-2002-2867"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengqi Niu","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042363663","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0001-7505-1767"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Hu","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101667364","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0002-9131-5854"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.8523,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74188766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13717","display_name":"Advanced Algorithms and Applications","score":0.8367999792098999,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13717","display_name":"Advanced Algorithms and Applications","score":0.8367999792098999,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.7840999960899353,"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/T14225","display_name":"Advanced Sensor and Control Systems","score":0.7746000289916992,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7863385677337646},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6750451326370239},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5698402523994446},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.54425048828125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5423546433448792},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38364559412002563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7863385677337646},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6750451326370239},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5698402523994446},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.54425048828125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5423546433448792},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38364559412002563}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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":30,"referenced_works":["https://openalex.org/W1996512145","https://openalex.org/W2154278880","https://openalex.org/W2407044469","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2808631503","https://openalex.org/W2883725317","https://openalex.org/W2890964092","https://openalex.org/W2969985801","https://openalex.org/W2981087920","https://openalex.org/W2993724474","https://openalex.org/W3163421828","https://openalex.org/W3197848469","https://openalex.org/W3198275944","https://openalex.org/W3206189675","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4210812844","https://openalex.org/W4226380987","https://openalex.org/W4248165172","https://openalex.org/W4287832069","https://openalex.org/W4304091753","https://openalex.org/W4311137818","https://openalex.org/W4366147765","https://openalex.org/W4372262420","https://openalex.org/W4375868932","https://openalex.org/W4385822451","https://openalex.org/W4392931801","https://openalex.org/W6728550200","https://openalex.org/W6857495872"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W2033914206","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W2042327336","https://openalex.org/W289407349"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,10,19,27,130],"novel":[6],"loss":[7,14,22,39,65,118],"by":[8,56,78],"integrating":[9],"deep":[11],"clustering":[12],"(DC)":[13],"at":[15,23],"the":[16,24,63,69,75,79,92,97,103,110,113,125,136],"frame-level":[17,47],"and":[18,34,87,128],"speaker":[20,54],"recognition":[21],"segment-level":[25],"into":[26],"single":[28],"network":[29],"without":[30],"additional":[31],"data":[32],"requirements":[33],"exhaustive":[35],"computation.":[36],"The":[37,116],"DC":[38,64],"implicitly":[40],"generates":[41],"soft":[42],"pseudo-phoneme":[43],"labels":[44],"for":[45,122,133],"each":[46],"feature,":[48,71],"which":[49],"facilitates":[50],"extracting":[51],"more":[52],"discriminant":[53],"representation":[55],"suppressing":[57],"phonetic":[58],"content":[59],"information.":[60],"We":[61],"study":[62],"not":[66],"only":[67],"on":[68,74,91,102,112,124,135],"acoustic":[70,114,126],"but":[72],"also":[73],"features":[76,106],"extracted":[77],"pre-trained":[80,104,137],"models,":[81],"such":[82],"as":[83],"wav2vec":[84],"2.0,":[85],"HuBERT":[86],"WavLM.":[88],"Experimental":[89],"results":[90],"VoxCeleb":[93],"dataset":[94],"shows":[95],"that":[96],"overall":[98],"system":[99],"performance":[100],"based":[101],"model":[105,138],"are":[107],"better":[108],"than":[109],"one":[111],"feature.":[115,139],"proposed":[117],"is":[119],"significantly":[120],"effective":[121],"systems":[123,134],"feature":[127],"has":[129],"marginal":[131],"improvement":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}