DeepAI AI Chat
Log In Sign Up

SapAugment: Learning A Sample Adaptive Policy for Data Augmentation

by   Ting-yao Hu, et al.

Data augmentation methods usually apply the same augmentation (or a mix of them) to all the training samples. For example, to perturb data with noise, the noise is sampled from a Normal distribution with a fixed standard deviation, for all samples. We hypothesize that a hard sample with high training loss already provides strong training signal to update the model parameters and should be perturbed with mild or no augmentation. Perturbing a hard sample with a strong augmentation may also make it too hard to learn from. Furthermore, a sample with low training loss should be perturbed by a stronger augmentation to provide more robustness to a variety of conditions. To formalize these intuitions, we propose a novel method to learn a Sample-Adaptive Policy for Augmentation – SapAugment. Our policy adapts the augmentation parameters based on the training loss of the data samples. In the example of Gaussian noise, a hard sample will be perturbed with a low variance noise and an easy sample with a high variance noise. Furthermore, the proposed method combines multiple augmentation methods into a methodical policy learning framework and obviates hand-crafting augmentation parameters by trial-and-error. We apply our method on an automatic speech recognition (ASR) task, and combine existing and novel augmentations using the proposed framework. We show substantial improvement, up to 21 state-of-the-art speech augmentation method.


page 1

page 2

page 3

page 4


Self-paced Data Augmentation for Training Neural Networks

Data augmentation is widely used for machine learning; however, an effec...

A Comparison of Speech Data Augmentation Methods Using S3PRL Toolkit

Data augmentations are known to improve robustness in speech-processing ...

A Policy-based Approach to the SpecAugment Method for Low Resource E2E ASR

SpecAugment is a very effective data augmentation method for both HMM an...

On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR

We propose an on-the-fly data augmentation method for automatic speech r...

An Improved Data Augmentation Scheme for Model Predictive Control Policy Approximation

This paper considers the problem of data generation for MPC policy appro...

Learning Noise-Invariant Representations for Robust Speech Recognition

Despite rapid advances in speech recognition, current models remain brit...

Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments

Image recognition models that can work in challenging environments (e.g....