Masked Audio Generation using a Single Non-Autoregressive Transformer

research work·research paper·active

Research work examining audio generation, text-to-audio generation.

Recorded facts

Official site	https://arxiv.org/abs/2401.04577 ↗
Geography	Global
arxiv	2401.04577
venue	arXiv preprint
authors	Alon Ziv; Itai Gat; Gael Le Lan; Tal Remez; Felix Kreuk; Alexandre Défossez; Jade Copet; Gabriel Synnaeve; Yossi Adi
methods	transformer architecture
code urls	unknown
demo urls	unknown
exact title	Masked Audio Generation using a Single Non-Autoregressive Transformer
project urls	https://pages.cs.huji.ac.il/adiyoss-lab/MAGNeT
original title	unknown
citation counts	unknown
research topics	audio generation; text-to-audio generation; text-to-music generation
peer review status	not established from abstract metadata
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	2024-01-09
abstract level neutral summary	The work studies audio generation, text-to-audio generation; methods and evaluation details are in the official abstract.
datasets benchmarks models tools used	unknown
correction withdrawal retraction status	No withdrawal marker observed in captured arXiv metadata.

affiliated with	Meta 2024-01-09 — nowSource 1 ↗ VERIFIED medium confidence
introduces	MAGNeT Small 10s 2024-01-09 — nowSource 1 ↗ VERIFIED high confidence
introduces	MAGNeT Medium 10s 2024-01-09 — nowSource 1 ↗ VERIFIED high confidence
introduces	MAGNeT Small 30s 2024-01-09 — nowSource 1 ↗ VERIFIED high confidence
introduces	MAGNeT Medium 30s 2024-01-09 — nowSource 1 ↗ VERIFIED high confidence