Sound field image dataset

<p><strong>Description</strong></p> <p>This&nbsp;<strong>sound field image dataset</strong>&nbsp;contains clean-noisy pairs of complex-valued sound-field images generated by 2D acoustic simulations. The dataset was&nbsp;initially prepared for&nbsp;<strong>deep sound-field denoiser&nbsp;</strong>(<a href="https://github.com/nttcslab/deep-sound-field-denoiser">https://github.com/nttcslab/deep-sound-field-denoiser</a>)<strong>,</strong>&nbsp;a DNN-based denoising method for optically measured sound fields. Since the data is a two-dimensional sound field based on the Helmholtz equation, one can use this dataset for any acoustic application. Please check our <a href="https://github.com/nttcslab/deep-sound-field-denoiser">GitHub repository</a> and <a href="https://arxiv.org/abs/2304.14923">paper</a> for details.</p> <p>&nbsp;</p> <p><strong>Directory structure</strong></p> <p>The dataset contains three directories: training, validation, and evaluation. Each directory contains &quot;soundsource#&quot; sub-directories (# represents the number of sound sources used in the acoustic simulation). Each sub-directory has three h5 files for data (clean, white noise, and speckle noise) and three CSV files listing random parameter values used in the simulation.</p> <p>- /training</p> <p>&nbsp; &nbsp; - /soundsource#</p> <p>&nbsp; &nbsp; &nbsp; &nbsp;- constants.csv</p> <p>&nbsp; &nbsp; &nbsp; &nbsp;- random_variable_ranges.csv</p> <p>&nbsp; &nbsp; &nbsp; &nbsp;- random_variables.csv</p> <p>&nbsp; &nbsp; &nbsp; &nbsp;- sf_true.h5</p> <p>&nbsp; &nbsp; &nbsp; &nbsp;- sf_noise_white.h5</p> <p>&nbsp; &nbsp; &nbsp; &nbsp;- sf_noise_speckle.h5</p> <p>&nbsp;</p> <p><strong>Condition of use</strong></p> <p>This dataset is available&nbsp;under the attached license file.&nbsp;Read the terms and conditions in&nbsp;NTTSoftwareLicenseAgreement.pdf carefully.</p> <p>&nbsp;</p> <p><strong>Citation</strong></p> <p>If you use this dataset, please cite the following paper.</p> <ul> <li> <p>K. Ishikawa, D. Takeuchi, N. Harada, and T. Moriya ``Deep sound-field denoiser: optically-measured sound-field denoising using deep neural network,&#39;&#39; arXiv:2304.14923 (2023).</p> </li> </ul>