MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models
This addresses the challenge of iterative music refinement for creators using generative AI, though it is incremental as it builds on existing diffusion models.
The paper tackles the problem of editing music generated by text-to-music models, enabling modification of attributes like genre or mood while preserving other aspects, and demonstrates superior performance over baselines in style and timbre transfer evaluations.
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.