MusicFlow: Cascaded Flow Matching for Text Guided Music Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Prajwal, K R, Shi, Bowen, Lee, Matthew, Vyas, Apoorv, Tjandra, Andros, Luthra, Mahi, Guo, Baishan, Wang, Huiyu, Afouras, Triantafyllos, Kant, David, Hsu, Wei-Ning
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913565555818496
author Prajwal, K R
Shi, Bowen
Lee, Matthew
Vyas, Apoorv
Tjandra, Andros
Luthra, Mahi
Guo, Baishan
Wang, Huiyu
Afouras, Triantafyllos
Kant, David
Hsu, Wei-Ning
author_facet Prajwal, K R
Shi, Bowen
Lee, Matthew
Vyas, Apoorv
Tjandra, Andros
Luthra, Mahi
Guo, Baishan
Wang, Huiyu
Afouras, Triantafyllos
Kant, David
Hsu, Wei-Ning
contents 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. Our code and model will be publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20478
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MusicFlow: Cascaded Flow Matching for Text Guided Music Generation
Prajwal, K R
Shi, Bowen
Lee, Matthew
Vyas, Apoorv
Tjandra, Andros
Luthra, Mahi
Guo, Baishan
Wang, Huiyu
Afouras, Triantafyllos
Kant, David
Hsu, Wei-Ning
Sound
Artificial Intelligence
Audio and Speech Processing
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. Our code and model will be publicly available.
title MusicFlow: Cascaded Flow Matching for Text Guided Music Generation
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2410.20478