Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Yixiao Zhang, Yukara Ikemiya, Gus Xia, Naoki Murata, Marco A. Mart\'inez-Ram\'irez, Wei-Hsiang Liao, Yuki Mitsufuji, Simon Dixon• 2024

Related benchmarks

TaskDatasetResultRank
Timbre TransferMusicDelta
CLAP0.238
8
Timbre TransferMUSDB18 HQ (test)
CLAP0.187
8
Music EditingZoME-Bench Genre
CLAP28.3
6
Music EditingMusic Editing Subjective (evaluation)
Target Attribute Match (T)2.92
6
Music EditingZoME-Bench Instrument
CLAP21.7
6
Showing 5 of 5 rows

Other info

Follow for update