We present a novel architecture for a synthesizer based on an autoencoder that compresses and reconstructs magnitude short time Fourier transform frames. This architecture outperforms previous topologies by using improved regularization, employing several activation functions, creating a focused training corpus, and implementing the Adam learning method. By multiplying gains to the hidden layer, users can alter the autoencoder’s output, which opens up a palette of sounds unavailable to additive/subtractive synthesizers. Furthermore, our architecture can be quickly re-trained on any sound domain, making it flexible for music synthesis applications. Samples of the autoencoder’s outputs can be found at http://soundcloud.com/ann_synth , and the code used to generate and train the autoencoder is open source, hosted at http://github.com/JTColonel/ann_synth.

Authors: Colonel, Joseph; Curro, Christopher; Keene, Sam
Affiliation: The Cooper Union for the Advancement of Science and Art, New York, NY, USA
AES Convention: 143 (October 2017) Paper Number: 9846
Publication Date: October 8, 2017 Import into BibTeX
Subject: Signal Processing
Permalink: http://www.aes.org/e-lib/browse.cfm?elib=19243

Download Now (308 KB)

This paper is Open Access which means you can download it for free.

Learn more about the AES E-Library

E-Library Location:   /conv/143/9846.pdf

Start a discussion about this paper!