TimbreCLIP: Connecting Timbre to Text and Images

11/21/2022

∙

by   Nicolas Jonason, et al.

∙

0

∙

share

We present work in progress on TimbreCLIP, an audio-text cross modal embedding trained on single instrument notes. We evaluate the models with a cross-modal retrieval task on synth patches. Finally, we demonstrate the application of TimbreCLIP on two tasks: text-driven audio equalization and timbre to image generation.