MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models

TL;DR

MusicMagus enables precise, zero-shot editing of generated music by manipulating latent space in diffusion models, allowing changes in genre, mood, and instruments without retraining, thus advancing flexible musical creativity.

Contribution

Introduces a novel latent space manipulation method for zero-shot music editing that integrates with existing diffusion models without additional training.

Findings

Outperforms zero-shot and supervised baselines in style and timbre transfer

Maintains musical content while editing specific attributes

Demonstrates practical applicability in real-world scenarios

Abstract

Recent advances in text-to-music generation models have opened new avenues in musical creativity. However, music generation usually involves iterative refinements, and how to edit the generated music remains a significant challenge. This paper introduces a novel approach to the editing of music generated by such models, enabling the modification of specific attributes, such as genre, mood and instrument, while maintaining other aspects unchanged. Our method transforms text editing to \textit{latent space manipulation} while adding an extra constraint to enforce consistency. It seamlessly integrates with existing pretrained text-to-music diffusion models without requiring additional training. Experimental results demonstrate superior performance over both zero-shot and certain supervised baselines in style and timbre transfer evaluations. Additionally, we showcase the practical applicability of our approach in real-world music editing scenarios.