MusicFlow: Cascaded Flow Matching for Text Guided Music Generation
Abstract
We introduce MusicFlow, a cascaded text-to-music generation model based on flow matching. Based on self-supervised representations to bridge between text descriptions and music audios, we construct two flow matching networks to model the conditional distribution of semantic and acoustic features. Additionally, we leverage masked prediction as the training objective, enabling the model to generalize to other tasks such as music infilling and continuation in a zero-shot manner. Experiments on MusicCaps reveal that the music generated by MusicFlow exhibits superior quality and text coherence despite being over $2\sim5$ times smaller and requiring $5$ times fewer iterative steps. Simultaneously, the model can perform other music generation tasks and achieves competitive performance in music infilling and continuation.
Cite
Text
Prajwal et al. "MusicFlow: Cascaded Flow Matching for Text Guided Music Generation." International Conference on Machine Learning, 2024.Markdown
[Prajwal et al. "MusicFlow: Cascaded Flow Matching for Text Guided Music Generation." International Conference on Machine Learning, 2024.](https://mlanthology.org/icml/2024/prajwal2024icml-musicflow/)BibTeX
@inproceedings{prajwal2024icml-musicflow,
title = {{MusicFlow: Cascaded Flow Matching for Text Guided Music Generation}},
author = {Prajwal, K R and Shi, Bowen and Le, Matthew and Vyas, Apoorv and Tjandra, Andros and Luthra, Mahi and Guo, Baishan and Wang, Huiyu and Afouras, Triantafyllos and Kant, David and Hsu, Wei-Ning},
booktitle = {International Conference on Machine Learning},
year = {2024},
pages = {41052-41063},
volume = {235},
url = {https://mlanthology.org/icml/2024/prajwal2024icml-musicflow/}
}