MusicFlow: Cascaded Flow Matching for Text Guided Music Generation
K R Prajwal, Bowen Shi, Matthew Le, Apoorv Vyas, Andros Tjandra, Mahi Luthra, Baishan Guo, Huiyu Wang
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.
BibTeX
@inproceedings{
prajwal2024musicflow,
title={MusicFlow: Cascaded Flow Matching for Text Guided Music Generation},
author={K R Prajwal and Bowen Shi and Matthew Le and Apoorv Vyas and Andros Tjandra and Mahi Luthra and Baishan Guo and Huiyu Wang and Triantafyllos Afouras and David Kant and Wei-Ning Hsu},
booktitle={Forty-first International Conference on Machine Learning},
year={2024},
url={https://openreview.net/forum?id=kOczKjmYum}
}