Skip to content

Audio to Image & Image to Audio

A combination of machine learning algorithms and computer vision techniques will be explored in order to generate visual representations from sounds and soundscapes from images, using multimodal features. The power of Generative Adversarial Networks (GANs) will also be investigated in the context of this activity aiming at the development of new tools for the creation of artistic instances in line with ReSilence’s artistically driven approach.