Towards an Accessible and Rapidly Trainable Rhythm Sequencer Using a Generative Stacked Autoencoder

TL;DR

This paper introduces a generative stacked autoencoder-based rhythm sequencer integrated into a melodic step-sequencer, aiming to make AI-assisted music creation accessible and rapid for electronic music practitioners.

Contribution

It presents a novel integration of generative autoencoders into a rhythm sequencer, focusing on accessibility and ease of use for non-expert musicians.

Findings

Models show creative potential despite limitations.

The approach enhances accessibility for music practitioners.

Viable solutions for AI-assisted rhythm generation are demonstrated.

Abstract

Neural networks and deep learning are often deployed for the sake of the most comprehensive music generation with as little involvement as possible from the human musician. Implementations in aid of, or being a tool for, music practitioners are sparse. This paper proposes the integration of generative stacked autoencoder structures for rhythm generation, within a conventional melodic step-sequencer. It further aims to work towards its implementation being accessible to the average electronic music practitioner. Several model architectures have been trained and tested for their creative potential. While the currently implementations do display limitations, they do represent viable creative solutions for music practitioners.