In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN). In training, Random Erasing randomly selects a rectangle region in an image and erases its pixels with random values. In this process, training images with various levels of occlusion are generated, which reduces the risk of over-fitting and makes the model robust to o...

Linear regression based speaker adaptation approaches can improve Automatic Speech Recognition (ASR) accuracy significantly for a target speaker. However, when the available adaptation data is limited to a few seconds, the accuracy of the speaker adapted models is often worse compared with speaker independent models. In this paper, we propose an approach to select a set of reference speakers ac...

The problem of formal likelihood-based (either classical or Bayesian) inference for discretely observed multi-dimensional diffusions is particularly challenging. In principle this involves data-augmentation of the observation data to give representations of the entire diffusion trajectory. Most currently proposed methodology splits broadly into two classes: either through the discretisation of ...

Advanced data augmentation techniques have demonstrated great success in deep learning algorithms. Among these techniques, single-image-based (SIBDA), which a single image’s regions are randomly erased different ways, has shown promising results. However, erasing image SIBDA can cause loss of the key discriminating features, consequently misleading neural networks and lowering their performance...