In supervised speech separation, permutation invariant training (PIT) is
widely used to handle label ambiguity by selecting the best permutation to
update the model. Despite its success, previous studies showed that PIT is
plagued by excessive label assignment switching in adjacent epochs, impeding
the model to learn better label assignments. To address this issue, we propose
a novel training strategy, dynamic sample dropout (DSD), which considers
previous best label assignments and evaluation metrics to exclude the samples
that may negatively impact the learned label assignments during training.
Additionally, we include layer-wise optimization (LO) to improve the
performance by solving layer-decoupling. Our experiments showed that combining
DSD and LO outperforms the baseline and solves excessive label assignment
switching and layer-decoupling issues. The proposed DSD and LO approach is easy
to implement, requires no extra training sets or steps, and shows generality to
various speech separation tasks.

在受监督语音分离中，我们提出了一种新的训练策略，动态样本丢失（DSD），它考虑了先前的最佳标签分配和评估指标，以排除在训练期间可能对学习到的标签分配产生负面影响的样本，并且通过层解耦方法（LO）来解决层解耦问题，结果表明，结合 DSD 和 LO 的方法优于基准方法，解决了过多的标签分配变换和层解耦问题，该方法易于实现，无需额外的训练集或步骤，并且适用于各种语音分离任务。