In speech deepfake detection (SDD), data augmentation (DA) is commonly used to improve model generalization across varied speech conditions and spoofing attacks. However, during training, the backpropagated gradients from original and augmented inputs may misalign, which can result in conflicting parameter updates. These conflicts could hinder convergence and push the model toward suboptimal solutions, thereby reducing the benefits of DA. To investigate and address this issue, we design a dual-path data-augmented (DPDA) training framework with gradient alignment for SDD. In our framework, each training utterance is processed through two input paths: one using the original speech and the other with its augmented version. This design allows us to compare and align their backpropagated gradient directions to reduce optimization conflicts. Our analysis shows that approximately 25% of training iterations exhibit gradient conflicts between the original inputs and their augmented counterparts when using RawBoost augmentation. By resolving these conflicts with gradient alignment, our method accelerates convergence by reducing the number of training epochs and achieves up to an 18.69% relative reduction in Equal Error Rate on the In-the-Wild dataset compared to the baseline.

翻译：在语音深度伪造检测（SDD）中，数据增强（DA）通常用于提升模型在不同语音条件和欺骗攻击下的泛化能力。然而，在训练过程中，来自原始输入与增强输入的反向传播梯度可能出现失配，这可能导致参数更新产生冲突。这些冲突可能阻碍模型收敛，并将模型推向次优解，从而降低数据增强的收益。为探究并解决此问题，我们设计了一种面向SDD的、具有梯度对齐机制的双路径数据增强（DPDA）训练框架。在我们的框架中，每个训练话语通过两个输入路径处理：一路使用原始语音，另一路使用其增强版本。这一设计使我们能够比较并对齐其反向传播梯度的方向，从而减少优化冲突。我们的分析表明，在使用RawBoost增强方法时，约有25%的训练迭代在原始输入与其增强版本之间表现出梯度冲突。通过梯度对齐解决这些冲突后，我们的方法通过减少训练周期数加速了收敛，并在In-the-Wild数据集上相比基线实现了高达18.69%的等错误率相对降低。