Fig. 3From: Synthesis of soundfields through irregular loudspeaker arrays based on convolutional neural networksSchematic representation of the training procedure. Note that for simplicity, the images of \(\textbf{p}_{\text {cnn}}\) and \(\textbf{p}\) correspond only the real part of the amplitude pressure soundfield obtained at a frequency \(f=562\ \text {Hz}\) and due to a source positioned in \(\textbf{r}=[-0.61\ \text {m}, 1.42\ \text {m}]^T\)Back to article page