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.
MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models
Latent space manipulation allows for the editing of music generated from text, enabling attribute-specific changes while maintaining consistency, demonstrated superior performance in style and timbre transfer, and is applicable in real-world scenarios.
- Year
- 2024
- Venue
- arXiv 2024
- Authors
- 8
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2402.06178v3ARXIV-DEFAULT
- TL;DR
- Semantic Scholar