Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.06897 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913194334748672 |
|---|---|
| author | Ye, Zuzhao Ciccarelli, Gregory Kulis, Brian |
| author_facet | Ye, Zuzhao Ciccarelli, Gregory Kulis, Brian |
| contents | Data augmentation is a key tool for improving the performance of deep networks, particularly when there is limited labeled data. In some fields, such as computer vision, augmentation methods have been extensively studied; however, for speech and audio data, there are relatively fewer methods developed. Using adversarial learning as a starting point, we develop a simple and effective augmentation strategy based on taking the gradient of the entropy of the outputs with respect to the inputs and then creating new data points by moving in the direction of the gradient to maximize the entropy. We validate its efficacy on several keyword spotting tasks as well as standard audio benchmarks. Our method is straightforward to implement, offering greater computational efficiency than more complex adversarial schemes like GANs. Despite its simplicity, it proves robust and effective, especially when combined with the established SpecAugment technique, leading to enhanced performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_06897 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Maximum-Entropy Adversarial Audio Augmentation for Keyword Spotting Ye, Zuzhao Ciccarelli, Gregory Kulis, Brian Audio and Speech Processing Data augmentation is a key tool for improving the performance of deep networks, particularly when there is limited labeled data. In some fields, such as computer vision, augmentation methods have been extensively studied; however, for speech and audio data, there are relatively fewer methods developed. Using adversarial learning as a starting point, we develop a simple and effective augmentation strategy based on taking the gradient of the entropy of the outputs with respect to the inputs and then creating new data points by moving in the direction of the gradient to maximize the entropy. We validate its efficacy on several keyword spotting tasks as well as standard audio benchmarks. Our method is straightforward to implement, offering greater computational efficiency than more complex adversarial schemes like GANs. Despite its simplicity, it proves robust and effective, especially when combined with the established SpecAugment technique, leading to enhanced performance. |
| title | Maximum-Entropy Adversarial Audio Augmentation for Keyword Spotting |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2401.06897 |