Latent Jamming with RAVE: Neural audio realtime intervention in latent space using nn~ in Pure Data

In this video I'm presenting a practice I call Latent Jamming in which I simulate latent embeddings by employing signal generators and translate them into audio information using a RAVE model's decoder.
Latent Jamming is an explorative technique which includes finding interesting seeds, playing around with signal range spread and offsets each per latent dimension as provided by model and nn~ as well as conserving constellations and patterns.

The model has been trained on my own body of work.

---

RAVE is "A variational autoencoder for fast and high-quality neural audio synthesis” created by Antoine Caillon and Philippe Esling of Artificial Creative Intelligence and Data Science (ACIDS) at IRCAM, Paris.

RAVE on GitHub: https://github.com/acids-ircam/RAVE
nn~ on GitHub: https://github.com/acids-ircam/nn_tilde

To train models on Colab or Kaggle, you can use these Jupyter notebooks i've set up: https://github.com/devstermarts/Noteb...