Sound field image dataset

Description

This sound field image dataset contains clean-noisy pairs of complex-valued sound-field images generated by 2D acoustic simulations. The dataset was initially prepared for deep sound-field denoiser (https://github.com/nttcslab/deep-sound-field-denoiser), 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 GitHub repository and paper for details.

Directory structure

The dataset contains three directories: training, validation, and evaluation. Each directory contains "soundsource#" 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.

- /training

    - /soundsource#

       - constants.csv

       - random_variable_ranges.csv

       - random_variables.csv

       - sf_true.h5

       - sf_noise_white.h5

       - sf_noise_speckle.h5

Condition of use

This dataset is available under the attached license file. Read the terms and conditions in NTTSoftwareLicenseAgreement.pdf carefully.

Citation

If you use this dataset, please cite the following paper.

K. Ishikawa, D. Takeuchi, N. Harada, and T. Moriya ``Deep sound-field denoiser: optically-measured sound-field denoising using deep neural network,'' arXiv:2304.14923 (2023).