Skip to main content
Fig. 4 | EURASIP Journal on Audio, Speech, and Music Processing

Fig. 4

From: Points2Sound: from mono to binaural audio using 3D point cloud scenes

Fig. 4

Envelope Distance (\(\mathrm {d}_{\mathrm {ENV}}\)) and STFT Distance (\(\mathrm {d}_\mathrm {STFT}\)) of Points2Sound (\(\mathcal {L}_{\mathrm {full}}\)), trained in anechoic conditions, for different rooms and number of sources in the 3D scene. The results are reported using rgb-depth point cloud features. For each number of sources, the box extension shows the first and third quartile of the data with a line at the median. The whiskers extending from the box show the range of the data

Back to article page