Sound field image with objects dataset

Description This sound field image with objects dataset contains clean-noisy pairs of complex-valued sound-field images generated by 2D acoustic simulations. The dataset was initially prepared for SoundSil-DS (https://github.com/nttcslab/soundsil-ds), a DNN-based denoising method for optically measured sound fields. 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 object-mask) and one CSV file listing random parameter values used in the simulation. - /training - /soundsource# - sf_true.h5 - sf_noise_white.h5 - mask_data.h5 - random_variables.csv### 数据集描述 本带目标物体声场图像数据集包含由二维声学仿真生成的复数值声场图像清洁-噪声配对样本。本数据集最初为SoundSil-DS（https://github.com/nttcslab/soundsil-ds）构建，该工具是一种针对光学测量声场的基于深度神经网络（Deep Neural Network，DNN）的去噪方法。详细信息请查阅我们的GitHub仓库与相关论文。 ### 目录结构 本数据集包含训练、验证与评估三个目录。每个目录下均设有以"soundsource#"命名的子目录（其中#代表声学仿真中使用的声源数量）。每个子目录包含3个.h5文件（分别对应清洁声场、白噪声与目标物体掩码），以及1个记录仿真所用随机参数值的CSV文件。 - /training - /soundsource# - sf_true.h5 - sf_noise_white.h5 - mask_data.h5 - random_variables.csv