EVxRAVE: Incorporating Neural Synthesis in an Augmented String Instrument Platform

The EV is an augmented bowed string instrument that integrates digital signal processing with acoustic performance. This demo presents EVxRAVE, the incorporation of IRCAM’s RAVE variational autoencoder into the instrument. Trained on recordings of the EV itself, the model yields an eight-dimensional latent space that can be navigated in performance through pitch, amplitude, spectral features, low-frequency oscillators, and other control sources. The accompanying performance, two tales from the shadows of the grid, demonstrates contrasting modes of interaction—balancing automated modulation with embodied gesture, and exploring how AI can serve as a self-referential layer of timbral expression within a traditional string paradigm.