This paper addresses audio classification with limited training resources. We first investigate different types of data augmentation including physical modeling, wavelet scattering transform and Generative Adversarial Networks (GAN). We than propose a novel GAN which allows embedding of physical augmentation and wavelet scattering transform in processing. The experimental results on Google Speech Command show significant improvements of the proposed method when training with limited resources. It could lift up classification accuracy from the best baselines of 62.06% and 77.29% on ResNet, to as far as 91.96% and 93.38%, when training with 10% and 25% training data, respectively.