Auditory Attention Detection Dataset Nanjing University

<p>Auditory Attention Detection Dataset</p> <p>The experiment is conducted by Yuanming, Zhang and Ziyan, Yuan, supervised by Jing, Lu.</p> <p>&nbsp;</p> <p>Two zip files are included in this dataset.</p> <p>The script.zip file contains several scripts to divide each trial into several parts. These scripts are useful if you want to split the dataset into training, validation and test set.</p> <p>The other zip file contains the preprocessed EEG and audio signals. (Not the raw EEG!)</p> <p>Each mat file contains EEG and audio signals from one subject. Their are two variables named <strong><em>expinfo</em></strong> and <strong><em>data</em></strong>.</p> <p>The <em><strong>expinfo </strong></em>contains the attended direction information and audio stimulus playback information of each trial of the experiments. The azimuth column in <em><strong>expinfo </strong></em>indicates the directions of the two competing speakers. The negative directions indicated the speaker coming from the left, and positive coming from the right.</p> <p>The <strong><em>data </em></strong>contains several essential fields relative to the EEG and audio signals. The <em><strong>data.eeg</strong></em> field is a cell array with 32 cell elements. Each cell contains the EEG signals in a single trial. And the index of the cell is the number of trial. The <em><strong>data.leftWav</strong></em> and <em><strong>data.rightWav</strong></em> field are original audio stimuli, and the <em><strong>data.leftEnv</strong></em> and <em><strong>data.rightEnv</strong></em> are the envelopes of the<em><strong> data.leftWav </strong></em>and <em><strong>data.rightWav</strong></em> respectively.</p> <p>The <em><strong>data.dim</strong></em> field tells you the physical meaning of each dimension of each signal, and the <em><strong>data.dim.chan.eeg</strong></em> contains the name of each channel of the EEG signal.</p>