Latent Space Oddity: Exploring Latent Spaces to Design Guitar Timbres
This work addresses the need for intuitive sound design tools for musicians, though it appears incremental as it builds on existing latent space methods.
The authors tackled the problem of modeling guitar amplifiers by introducing a convolutional network with an interpretable latent space, enabling musicians to combine or subtract characteristics of different amplifiers to design new guitar timbres.
We introduce a novel convolutional network architecture with an interpretable latent space for modeling guitar amplifiers. Leveraging domain knowledge of popular amplifiers spanning a range of styles, the proposed system intuitively combines or subtracts characteristics of different amplifiers, allowing musicians to design entirely new guitar timbres.