{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multiobjective-optimization-training-of-plda","title":"Multiobjective Optimization Training of PLDA for Speaker Verification","arxiv_id":"1808.08344","date":"2018-08-25","proceeding":null,"authors":["Liang He","Xianhong Chen","Can Xu","Jia Liu"],"abstract":"Most current state-of-the-art text-independent speaker verification systems\ntake probabilistic linear discriminant analysis (PLDA) as their backend\nclassifiers. The parameters of PLDA are often estimated by maximizing the\nobjective function, which focuses on increasing the value of log-likelihood\nfunction, but ignoring the distinction between speakers. In order to better\ndistinguish speakers, we propose a multi-objective optimization training for\nPLDA. Experiment results show that the proposed method has more than 10%\nrelative performance improvement in both EER and MinDCF on the NIST SRE14\ni-vector challenge dataset, and about 20% relative performance improvement in\nEER on the MCE18 dataset.","url_abs":"http://arxiv.org/abs/1808.08344v2","url_pdf":"http://arxiv.org/pdf/1808.08344v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multiobjective-optimization-training-of-plda","repo_url":"https://github.com/sanphiee/MOT-sGPLDA-MCE18","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"multiobjective-optimization-training-of-plda","repo_url":"https://github.com/sanphiee/MOT-sGPLDA-SRE14","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"multiobjective-optimization","task_name":"Multiobjective Optimization"},{"task_slug":"speaker-verification","task_name":"Speaker Verification"},{"task_slug":"text-independent-speaker-verification","task_name":"Text-Independent Speaker Verification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}