all AI news
Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification
April 26, 2024, 4:42 a.m. | Theo Lepage, Reda Dehak
cs.LG updates on arXiv.org arxiv.org
Abstract: Most state-of-the-art self-supervised speaker verification systems rely on a contrastive-based objective function to learn speaker representations from unlabeled speech data. We explore different ways to improve the performance of these methods by: (1) revisiting how positive and negative pairs are sampled through a "symmetric" formulation of the contrastive loss; (2) introducing margins similar to AM-Softmax and AAM-Softmax that have been widely adopted in the supervised setting. We demonstrate the effectiveness of the symmetric contrastive loss …
abstract art arxiv cs.lg data eess.as explore function learn margins negative performance positive speaker speech state systems through type verification
More from arxiv.org / cs.LG updates on arXiv.org
Sliced Wasserstein with Random-Path Projecting Directions
1 day, 17 hours ago |
arxiv.org
Learning Extrinsic Dexterity with Parameterized Manipulation Primitives
1 day, 17 hours ago |
arxiv.org
The Un-Kidnappable Robot: Acoustic Localization of Sneaking People
1 day, 17 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York