Network Modulation Synthesis: New Algorithms for Generating Musical Audio Using Autoencoder Networks

Abstract: A new framework is presented for generating musical audio using autoencoder neural networks. With the presented framework, called network modulation synthesis, users can create synthesis architectures and use novel generative algorithms to more easily move through the complex latent parameter space of an autoencoder model to create audio. Implementations of the new algorithms are provided for the open-source CANNe synthesizer network, and can be applied to other autoencoder networks for audio synthesis. Spectrograms and time-series encoding analysis demonstrate that the new algorithms provide simple mechanisms for users to generate time-varying parameter combinations, and therefore auditory possibilities, that are difficult to create by generating audio from handcrafted encodings.