A Neural Network Based Framework for Archetypical Sound Synthesis
Sound
2020-03-11 v2 Audio and Speech Processing
Abstract
This paper describes a preliminary approach to algorithmically reproduce the archetypical structure adopted by humans to classify sounds. In particular, we propose an approach to predict the human perceived chaos/order level in a sound and synthesize new timbres that present the desired amount of this feature. We adopted a Neural Network based method, in order to exploit its inner predisposition to model perceptive and abstract features. We finally discuss the obtained accuracy and possible implications in creative contexts.
Cite
@article{arxiv.2003.03160,
title = {A Neural Network Based Framework for Archetypical Sound Synthesis},
author = {Eric Guizzo and Alberto Novello},
journal= {arXiv preprint arXiv:2003.03160},
year = {2020}
}