Fact · Speech recognition
SpecAugment is a data augmentation method that is applied directly to a speech network's input features, the filter bank coefficients. It warps the features and masks blocks of frequency channels and blocks of time steps.
Checked against its source on October 17, 2026
In the source's own words
“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.”
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition, Daniel S. Park et al., Proceedings of Interspeech 2019, 2019, Abstract.
Open the original- What it measures
- The authors apply SpecAugment to Listen, Attend and Spell networks for end-to-end speech recognition, and report state-of-the-art results on the LibriSpeech and Switchboard benchmarks.
- What it does not show
- Augmentation is a training-time technique that makes a fixed dataset go further. It does not add new speakers or rooms, and the gains were measured on 2019 architectures.