flowEQ uses a disentangled variational autoencoder (β-VAE) in order to provide a new modality for modifying the timbre of recordings via a parametric equalizer. By traversing the learned latent space of the trained decoder network, the user can more quickly search through the configurations of a five band parametric equalizer. This methodology promotes using one’s ears to determine the proper EQ settings over looking at transfer functions or specific frequency controls. Two main modes of operation are provided (Traverse and Semantic), which allow users to sample from the latent space of the 12 trained models.
Quick and easy timbral adjustments
Automated timbral shifts over time for creative effects
Powerful 'tone controls' for users in a playback/listening setting
For more details on the plugin and VST/AU downloads checkout the project webpage.
flowEQ is open source and all of the code is available on GitHub. You can build the plugin yourself using MATLAB or modify and train the models yourself, with easy tools for importing them into the plugin.