使用正则化蒸馏框架推动自监督说话人验证的极限
Pushing the limits of self-supervised speaker verification using regularized distillation framework
AI总结：
本文针对无标签说话人验证任务，应用非对比自监督框架DINO并引入保证多样性与去相关变量的两个正则化项，结合时频域数据增强，在VoxCeleb上实现了单阶段自监督设置下的最优性能。
摘要：
在没有说话人标签的情况下训练鲁棒的说话人验证系统长期以来一直是一项具有挑战性的任务。先前的研究观察到自监督方法和全监督方法之间存在巨大的性能差距。在本文中，我们应用了一种称为DIstillation with NO labels (DINO) 的非对比自监督学习框架，并提出了应用于 DINO 中嵌入的两个正则化项。一个正则化项保证嵌入的多样性，而另一个正则化项去相关每个嵌入的变量。探索了各种数据增强技术在时域和频域上的有效性。在 VoxCeleb 数据集上进行的一系列实验证明了正则化 DINO 框架在说话人验证中的优越性。我们的方法在 VoxCeleb 上的单阶段自监督设置下实现了最先进的说话人验证性能。代码已在 https://github.com/alibaba-damo-academy/3D-Speaker 公开。
英文摘要：
Training robust speaker verification systems without speaker labels has long been a challenging task. Previous studies observed a large performance gap between self-supervised and fully supervised methods. In this paper, we apply a non-contrastive self-supervised learning framework called DIstillation with NO labels (DINO) and propose two regularization terms applied to embeddings in DINO. One regularization term guarantees the diversity of the embeddings, while the other regularization term decorrelates the variables of each embedding. The effectiveness of various data augmentation techniques are explored, on both time and frequency domain. A range of experiments conducted on the VoxCeleb datasets demonstrate the superiority of the regularized DINO framework in speaker verification. Our method achieves the state-of-the-art speaker verification performance under a single-stage self-supervised setting on VoxCeleb. Code has been made publicly available at https://github.com/alibaba-damo-academy/3D-Speaker.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
