Data augmentation (DA) has gained widespread popularity in deep speaker
models due to its ease of implementation and significant effectiveness. It
enriches training data by simulating real-life acoustic variations, enabling
deep neural networks to learn speaker-related representations while
disregarding irrelevant acoustic variations, thereby improving robustness and
generalization. However, a potential issue with the vanilla DA is augmentation
residual, i.e., unwanted distortion caused by different types of augmentation.
To address this problem, this paper proposes a novel approach called
adversarial data augmentation (A-DA) which combines DA with adversarial
learning. Specifically, it involves an additional augmentation classifier to
categorize various augmentation types used in data augmentation. This
adversarial learning empowers the network to generate speaker embeddings that
can deceive the augmentation classifier, making the learned speaker embeddings
more robust in the face of augmentation variations. Experiments conducted on
VoxCeleb and CN-Celeb datasets demonstrate that our proposed A-DA outperforms
standard DA in both augmentation matched and mismatched test conditions,
showcasing its superior robustness and generalization against acoustic
variations.

本文提出了一种名为对抗数据增强（A-DA）的新方法，将数据增强与对抗学习相结合，通过额外的分类器对不同类型的增强进行分类，使得网络能够生成能够欺骗分类器的说话者嵌入，从而提升模型对于增强变化的鲁棒性和泛化能力。在 VoxCeleb 和 CN-Celeb 数据集上的实验证明了我们提出的 A-DA 方法在匹配和不匹配的测试条件下均优于标准数据增强方法，展示了其对于声学变化的卓越鲁棒性和泛化能力。