LoopNet: Musical Loop Synthesis Conditioned On Intuitive Musical Parameters

TL;DR

LoopNet is a generative model that creates musical loops conditioned on intuitive parameters, enabling composers to easily produce and control loops based on musical criteria like rhythm and harmony.

Contribution

It introduces a novel feed-forward model using Wave-U-Net architecture conditioned on musical parameters, integrating MIR models and a large sample collection.

Findings

Effective loop generation conditioned on musical parameters

High-quality audio synthesis evaluated in the study

Intuitive control interface for composers

Abstract

Loops, seamlessly repeatable musical segments, are a cornerstone of modern music production. Contemporary artists often mix and match various sampled or pre-recorded loops based on musical criteria such as rhythm, harmony and timbral texture to create compositions. Taking such criteria into account, we present LoopNet, a feed-forward generative model for creating loops conditioned on intuitive parameters. We leverage Music Information Retrieval (MIR) models as well as a large collection of public loop samples in our study and use the Wave-U-Net architecture to map control parameters to audio. We also evaluate the quality of the generated audio and propose intuitive controls for composers to map the ideas in their minds to an audio loop.