English

Latent Space Oddity: Exploring Latent Spaces to Design Guitar Timbres

Sound 2020-11-23 v2 Machine Learning Audio and Speech Processing

Abstract

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.

Keywords

Cite

@article{arxiv.2010.15989,
  title  = {Latent Space Oddity: Exploring Latent Spaces to Design Guitar Timbres},
  author = {Jason Taylor},
  journal= {arXiv preprint arXiv:2010.15989},
  year   = {2020}
}

Comments

3 pages, 1 figure. To appear in the 2020 NeurIps Workshop on Machine Learning for Creativity and Design