AudRandAug: Random Image Augmentations for Audio Classification
This work addresses a gap in audio classification by adapting a proven image augmentation method, but it is incremental as it applies an existing technique to a new domain.
The authors tackled the lack of RandAug application for audio data by introducing AudRandAug, an adaptation that selects augmentation policies from an audio-specific search space, and found it outperforms existing methods in accuracy.
Data augmentation has proven to be effective in training neural networks. Recently, a method called RandAug was proposed, randomly selecting data augmentation techniques from a predefined search space. RandAug has demonstrated significant performance improvements for image-related tasks while imposing minimal computational overhead. However, no prior research has explored the application of RandAug specifically for audio data augmentation, which converts audio into an image-like pattern. To address this gap, we introduce AudRandAug, an adaptation of RandAug for audio data. AudRandAug selects data augmentation policies from a dedicated audio search space. To evaluate the effectiveness of AudRandAug, we conducted experiments using various models and datasets. Our findings indicate that AudRandAug outperforms other existing data augmentation methods regarding accuracy performance.