Simple and Controllable Music Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Copet, Jade, Kreuk, Felix, Gat, Itai, Remez, Tal, Kant, David, Synnaeve, Gabriel, Adi, Yossi, Défossez, Alexandre
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909086753226752
author Copet, Jade
Kreuk, Felix
Gat, Itai
Remez, Tal
Kant, David
Synnaeve, Gabriel
Adi, Yossi
Défossez, Alexandre
author_facet Copet, Jade
Kreuk, Felix
Gat, Itai
Remez, Tal
Kant, David
Synnaeve, Gabriel
Adi, Yossi
Défossez, Alexandre
contents We tackle the task of conditional music generation. We introduce MusicGen, a single Language Model (LM) that operates over several streams of compressed discrete music representation, i.e., tokens. Unlike prior work, MusicGen is comprised of a single-stage transformer LM together with efficient token interleaving patterns, which eliminates the need for cascading several models, e.g., hierarchically or upsampling. Following this approach, we demonstrate how MusicGen can generate high-quality samples, both mono and stereo, while being conditioned on textual description or melodic features, allowing better controls over the generated output. We conduct extensive empirical evaluation, considering both automatic and human studies, showing the proposed approach is superior to the evaluated baselines on a standard text-to-music benchmark. Through ablation studies, we shed light over the importance of each of the components comprising MusicGen. Music samples, code, and models are available at https://github.com/facebookresearch/audiocraft
format Preprint
id arxiv_https___arxiv_org_abs_2306_05284
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Simple and Controllable Music Generation
Copet, Jade
Kreuk, Felix
Gat, Itai
Remez, Tal
Kant, David
Synnaeve, Gabriel
Adi, Yossi
Défossez, Alexandre
Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
We tackle the task of conditional music generation. We introduce MusicGen, a single Language Model (LM) that operates over several streams of compressed discrete music representation, i.e., tokens. Unlike prior work, MusicGen is comprised of a single-stage transformer LM together with efficient token interleaving patterns, which eliminates the need for cascading several models, e.g., hierarchically or upsampling. Following this approach, we demonstrate how MusicGen can generate high-quality samples, both mono and stereo, while being conditioned on textual description or melodic features, allowing better controls over the generated output. We conduct extensive empirical evaluation, considering both automatic and human studies, showing the proposed approach is superior to the evaluated baselines on a standard text-to-music benchmark. Through ablation studies, we shed light over the importance of each of the components comprising MusicGen. Music samples, code, and models are available at https://github.com/facebookresearch/audiocraft
title Simple and Controllable Music Generation
topic Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2306.05284