On a time-frequency blurring operator with applications in data augmentation
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915558027427840 |
|---|---|
| author | Halvdansson, Simon |
| author_facet | Halvdansson, Simon |
| contents | Inspired by the success of recent data augmentation methods for signals which act on time-frequency representations, we introduce an operator which convolves the short-time Fourier transform of a signal with a specified kernel. Analytical properties including boundedness, compactness and positivity are investigated from the perspective of time-frequency analysis. A convolutional neural network and a vision transformer are trained to classify audio signals using spectrograms with different augmentation setups, including the above mentioned time-frequency blurring operator, with results indicating that the operator can significantly improve test performance, especially in the data-starved regime. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_12899 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On a time-frequency blurring operator with applications in data augmentation Halvdansson, Simon Functional Analysis Sound Audio and Speech Processing Inspired by the success of recent data augmentation methods for signals which act on time-frequency representations, we introduce an operator which convolves the short-time Fourier transform of a signal with a specified kernel. Analytical properties including boundedness, compactness and positivity are investigated from the perspective of time-frequency analysis. A convolutional neural network and a vision transformer are trained to classify audio signals using spectrograms with different augmentation setups, including the above mentioned time-frequency blurring operator, with results indicating that the operator can significantly improve test performance, especially in the data-starved regime. |
| title | On a time-frequency blurring operator with applications in data augmentation |
| topic | Functional Analysis Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2405.12899 |