What and When to Learn: CURriculum Ranking Loss for Large-Scale Speaker Verification
Speaker verification at large scale remains an open challenge as fixed-margin losses treat all samples equally regardless of quality. We hypothesize that mislabeled or degraded samples introduce noisy gradients that disrupt compact speaker manifolds. We propose Curry (CURriculum Ranking), an adaptive loss that estimates sample difficulty online via Sub-center ArcFace: confidence scores from dominant sub-center cosine similarity rank samples into easy, medium, and hard tiers using running batch statistics, without auxiliary annotations. Learnable weights guide the model from stable identity foundations through manifold refinement to boundary sharpening. To our knowledge, this is the largest-scale speaker verification system trained to date. Evaluated on VoxCeleb1-O, and SITW, Curry reduces EER by 86.8\% and 60.0\% over the Sub-center ArcFace baseline, establishing a new paradigm for robust speaker verification on imperfect large-scale data.
Code (0)
등록된 구현이 없습니다.
Tasks
Speaker VerificationSimilar Papers 제목 키워드 기반
Training Curricula for Open Domain Answer Re-Ranking
In precision-oriented tasks like answer ranking, it is more important to rank many relevant answers highly than to retrieve all relevant answers. It follows that a good ranking strategy would be to learn how to identify …
Re-RankingCurriculum Discovery through an Encompassing Curriculum Learning Framework
We describe a curriculum learning framework capable of discovering optimal curricula in addition to performing standard curriculum learning. We show that this framework encompasses existing curriculum learning approaches…
Natural Language Inferencetext-classificationText ClassificationMancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-identification
We propose a novel deep network called Mancs that solves the person re-identification problem from the following aspects: fully utilizing the attention mechanism for the person misalignment problem and properly sampling …
Person Re-IdentificationWhat do Language Models Learn and When? The Implicit Curriculum Hypothesis
Large language models (LLMs) can perform remarkably complex tasks, yet the fine-grained details of how these capabilities emerge during pretraining remain poorly understood. Scaling laws on validation loss tell us how mu…
Logical ReasoningWhen to Learn What: Model-Adaptive Data Augmentation Curriculum
Data augmentation (DA) is widely used to improve the generalization of neural networks by enforcing the invariances and symmetries to pre-defined transformations applied to input data. However, a fixed augmentation polic…
Data AugmentationFairnessimage-classificationImage Classification