Deep learning models have advanced the state of art monaural speech separation. However, performance a separation model considerably decreases when tested on unseen speakers and noisy conditions. Separation trained with data augmentation generalize better to In this paper, we conduct comprehensive survey techniques apply them improve generalization time-domain models. The include seven source-p...

Abstract Data augmentation has led to substantial improvements in the performance and generalization of deep models, remains a highly adaptable method evolving model architectures varying amounts data—in particular, extremely scarce available training data. In this paper, we present novel applying Möbius transformations augment input images during training. are bijective conformal maps that gen...

We present an automated data augmentation approach for image classification. formulate the problem as Monte Carlo sampling where our goal is to approximate optimal policies. propose a particle filtering formulation find policies and their schedules during model training. Our performance measurement procedure relies on validation subset of training set, while policy transition depends Gaussian p...

Dropout is typically interpreted as bagging a large number of models sharing parameters. We show that using dropout in a network can also be interpreted as a kind of data augmentation in the input space without domain knowledge. We present an approach to projecting the dropout noise within a network back into the input space, thereby generating augmented versions of the training data, and we sh...