SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Conference of the International Speech Communication Association, 2019.
We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients). The augmentation policy consists of warping the features, masking blocks of frequency channels, and masking blocks of time steps. We apply SpecAugment...More
Full Text (Upload PDF)