Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.21440 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915360121290752 |
|---|---|
| author | Leiber, Maxime Marnissi, Yosra Barrau, Axel Meignen, Sylvain Massoulié, Laurent |
| author_facet | Leiber, Maxime Marnissi, Yosra Barrau, Axel Meignen, Sylvain Massoulié, Laurent |
| contents | The short-time Fourier transform (STFT) is widely used for analyzing non-stationary signals. However, its performance is highly sensitive to its parameters, and manual or heuristic tuning often yields suboptimal results. To overcome this limitation, we propose a unified differentiable formulation of the STFT that enables gradient-based optimization of its parameters. This approach addresses the limitations of traditional STFT parameter tuning methods, which often rely on computationally intensive discrete searches. It enables fine-tuning of the time-frequency representation (TFR) based on any desired criterion. Moreover, our approach integrates seamlessly with neural networks, allowing joint optimization of the STFT parameters and network weights. The efficacy of the proposed differentiable STFT in enhancing TFRs and improving performance in downstream tasks is demonstrated through experiments on both simulated and real-world data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_21440 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform Leiber, Maxime Marnissi, Yosra Barrau, Axel Meignen, Sylvain Massoulié, Laurent Sound Machine Learning Audio and Speech Processing Signal Processing The short-time Fourier transform (STFT) is widely used for analyzing non-stationary signals. However, its performance is highly sensitive to its parameters, and manual or heuristic tuning often yields suboptimal results. To overcome this limitation, we propose a unified differentiable formulation of the STFT that enables gradient-based optimization of its parameters. This approach addresses the limitations of traditional STFT parameter tuning methods, which often rely on computationally intensive discrete searches. It enables fine-tuning of the time-frequency representation (TFR) based on any desired criterion. Moreover, our approach integrates seamlessly with neural networks, allowing joint optimization of the STFT parameters and network weights. The efficacy of the proposed differentiable STFT in enhancing TFRs and improving performance in downstream tasks is demonstrated through experiments on both simulated and real-world data. |
| title | Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform |
| topic | Sound Machine Learning Audio and Speech Processing Signal Processing |
| url | https://arxiv.org/abs/2506.21440 |