Simple and Controllable Music Generation

research work·research paper·active

Research work examining evaluation benchmark, music generation.

Recorded facts

Official site	https://arxiv.org/abs/2306.05284 ↗
Geography	Global
arxiv	2306.05284
venue	Published at Neurips 2023
authors	Jade Copet; Felix Kreuk; Itai Gat; Tal Remez; David Kant; Gabriel Synnaeve; Yossi Adi; Alexandre Défossez
methods	benchmark evaluation; language modeling; transformer architecture
code urls	https://github.com/facebookresearch/audiocraft
demo urls	https://github.com/facebookresearch/audiocraft
exact title	Simple and Controllable Music Generation
project urls	unknown
original title	unknown
citation counts	unknown
research topics	evaluation benchmark; music generation; music/audio representation learning; text-to-music generation
peer review status	venue or acceptance claim recorded in arXiv comment
disclosed conflicts	unknown
stated contribution	Presents or evaluates the system, method, benchmark, or analysis identified in the paper title.
us market scope basis	Included as a materially relevant public research artifact in the US-facing AI-music ecosystem; direct affiliation varies.
funding acknowledgements	unknown
affiliations at publication	Meta AI Research
publication or preprint date	2023-06-08
abstract level neutral summary	The work studies evaluation benchmark, music generation; methods and evaluation details are in the official abstract.
datasets benchmarks models tools used	MusicGen
correction withdrawal retraction status	No withdrawal marker observed in captured arXiv metadata.

affiliated with	Meta 2023-06-08 — nowSource 1 ↗ VERIFIED medium confidence
introduces	MusicGen Small 2023-06-08 — nowSource 1 ↗ VERIFIED high confidence
introduces	MusicGen Medium 2023-06-08 — nowSource 1 ↗ VERIFIED high confidence
introduces	MusicGen Melody 2023-06-08 — nowSource 1 ↗ VERIFIED high confidence
introduces	MusicGen Large 2023-06-08 — nowSource 1 ↗ VERIFIED high confidence