ToneTwist AFx Dataset: Custom Dynamic Fuzz

<div> <div> <h3><strong>Settings</strong></h3> <table> <tbody> <tr> <td>Gain</td> <td>Sensitivity</td> <td>Attack</td> <td>Release</td> <td>Volume</td> </tr> <tr> <td>5</td> <td>10</td> <td>1ms</td> <td>2500ms</td> <td>10</td> </tr> </tbody> </table> <h3><strong>Dry with markers</strong></h3> </div> </div> <p>Dry inputs are a selection of clean guitar and bass recordings from different sources:</p> <ul> <li><a href="https://www.idmt.fraunhofer.de/en/publications/datasets/guitar.html" target="_blank" rel="noopener">IDMT-SMT-GUITAR</a> - dataset 2 (7:23 min)</li> <li><a href="https://www.idmt.fraunhofer.de/en/publications/datasets/guitar.html" target="_blank" rel="noopener">IDMT-SMT-GUITAR</a> - dataset 4 - Career SG (6:08 min)</li> <li><a href="https://www.idmt.fraunhofer.de/en/publications/datasets/guitar.html" target="_blank" rel="noopener">IDMT-SMT-GUITAR</a> - dataset 4 - Ibanez 2820 (5:14 min)</li> <li><a href="https://www.idmt.fraunhofer.de/en/publications/datasets/bass_lines.html" target="_blank" rel="noopener">IDMT-SMT-Bass-Single-Track</a> - (5:58 min)</li> <li><a href="https://github.com/sdatkinson/neural-amp-modeler?tab=readme-ov-file#download-audio-files" target="_blank" rel="noopener">NAM: Neural Amp Modeler</a> - (3:11 min)</li> <li>Private Guitar Data - (5:19 min)</li> <li>YouTube Bass Recordings - (10:09 min)</li> </ul> <p>Pre-processing:</p> <ul> <li>All: <ul> <li>synchronization markers (2 impulses) added at start and end of every file</li> </ul> </li> <li>IDMT-SMT-GUITAR - dataset 2:<br> <ul> <li>peak normalized to -6dBFS</li> </ul> </li> <li>NAM:<br> <ul> <li>no pre-processing</li> </ul> </li> <li>Others:<br> <ul> <li>peak normalized to -0.1dBFS</li> <li>signal multiplied by random number every 5 seconds (uniform distribution [0.1, 1.0] = [-20dB, 0dB])</li> </ul> </li> </ul> <div> <h3><strong>Authors</strong></h3> <p><a href="https://mcomunita.github.io/" target="_blank" rel="noopener">Marco Comunit&agrave;</a> - <a href="http://c4dm.eecs.qmul.ac.uk/" target="_blank" rel="noopener">Centre for Digital Music</a>, Queen Mary University of London</p> <h3><strong>Github</strong></h3> <p><a href="https://github.com/mcomunita/tonetwist-afx-dataset" target="_blank" rel="noopener">https://github.com/mcomunita/tonetwist-afx-dataset</a></p> <h3><strong>Reference</strong></h3> <p>If you make use of this dataset, please cite the following publications:</p> <pre><code>@inproceedings{comunita2023modelling, title={Modelling black-box audio effects with time-varying feature modulation}, author={Comunit{\`a}, Marco and Steinmetz, Christian J and Phan, Huy and Reiss, Joshua D}, booktitle={ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pages={1--5}, year={2023}, organization={IEEE} }</code></pre> <pre>&nbsp;</pre> <pre><code>@misc{comunit&agrave;2025nablafxframeworkdifferentiableblackbox, title={NablAFx: A Framework for Differentiable Black-box and Gray-box Modeling of Audio Effects}, author={Marco Comunit&agrave; and Christian J. Steinmetz and Joshua D. Reiss}, year={2025}, eprint={2502.11668}, archivePrefix={arXiv}, primaryClass={cs.SD}, url={https://arxiv.org/abs/2502.11668}, }</code></pre> </div>