{"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/mask-proxy-loss-for-text-independent-speaker","title":"Masked Proxy Loss For Text-Independent Speaker Verification","arxiv_id":"2011.04491","date":"2020-11-09","proceeding":null,"authors":["Jiachen Lian","Aiswarya Vinod Kumar","Hira Dhamyal","Bhiksha Raj","Rita Singh"],"abstract":"Open-set speaker recognition can be regarded as a metric learning problem, which is to maximize inter-class variance and minimize intra-class variance. Supervised metric learning can be categorized into entity-based learning and proxy-based learning. Most of the existing metric learning objectives like Contrastive, Triplet, Prototypical, GE2E, etc all belong to the former division, the performance of which is either highly dependent on sample mining strategy or restricted by insufficient label information in the mini-batch. Proxy-based losses mitigate both shortcomings, however, fine-grained connections among entities are either not or indirectly leveraged. This paper proposes a Masked Proxy (MP) loss which directly incorporates both proxy-based relationships and pair-based relationships. We further propose Multinomial Masked Proxy (MMP) loss to leverage the hardness of speaker pairs. These methods have been applied to evaluate on VoxCeleb test set and reach state-of-the-art Equal Error Rate(EER).","url_abs":"https://arxiv.org/abs/2011.04491v2","url_pdf":"https://arxiv.org/pdf/2011.04491v2.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":"mask-proxy-loss-for-text-independent-speaker","repo_url":"https://github.com/jlian2/Masked-Proxy-Loss-for-Text-Indepedent-Speaker-Verification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"speaker-recognition","task_name":"Speaker Recognition"},{"task_slug":"speaker-verification","task_name":"Speaker Verification"},{"task_slug":"text-independent-speaker-recognition","task_name":"Text-Independent Speaker Recognition"},{"task_slug":"text-independent-speaker-verification","task_name":"Text-Independent Speaker Verification"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}