论文标题
针对嘈杂标签的演讲者验证的强大培训
Robust Training for Speaker Verification against Noisy Labels
论文作者
论文摘要
用于扬声器验证的深度学习模型在很大程度上取决于大量数据和正确的标签。但是，嘈杂（不正确）的标签经常发生，这会降低系统的性能。在本文中，我们提出了一种新颖的两阶段学习方法，以滤除扬声器数据集的嘈杂标签。由于DNN首先将数据与干净的标签拟合，因此我们首先使用几个时期的所有数据训练该模型。然后，基于此模型，使用我们提出的带有TOP-K机制的OR-GATE将模型预测与标签进行比较，以选择具有干净标签的数据，并且所选数据用于训练模型。此过程已迭代，直到培训完成为止。我们已经证明了这种方法通过广泛的实验过滤嘈杂的标签的有效性，并在Voxceleb（1和2）上实现了出色的性能，并具有不同的噪声速率。
The deep learning models used for speaker verification rely heavily on large amounts of data and correct labeling. However, noisy (incorrect) labels often occur, which degrades the performance of the system. In this paper, we propose a novel two-stage learning method to filter out noisy labels from speaker datasets. Since a DNN will first fit data with clean labels, we first train the model with all data for several epochs. Then, based on this model, the model predictions are compared with the labels using our proposed the OR-Gate with top-k mechanism to select the data with clean labels and the selected data is used to train the model. This process is iterated until the training is completed. We have demonstrated the effectiveness of this method in filtering noisy labels through extensive experiments and have achieved excellent performance on the VoxCeleb (1 and 2) with different added noise rates.
