SpecAugment

• SpecAugment: a Simple Data Augmentation Method for Automatic Speech Recognition
• simple data augmentation method for [speech recognition](speech recognition.md)
• applied directly to the feature inputs of a neural network
• warping the Features, masking blocks of frequency channels, and masking blocks of time steps
• apply SpecAugment on Listen, Attend and Spell (LAS) networks for end-to-end [speech recognition](speech recognition.md) tasks
• LibriSpeech
• Swichboard
• end-to-end LAS networks by augmenting the training set using simple handcrafted policies
• converts ASR from an over-Fitting to an under-Fitting problem, and they are able to gain performance by using bigger networks and training longer