AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining

research work·research paper·active

Research work examining audio generation, evaluation benchmark.

Verified facts

Official site	https://arxiv.org/abs/2308.05734 ↗
Geography	Global
arxiv	2308.05734
venue	Accepted by IEEE/ACM Transactions on Audio, Speech and Language Processing. Project page is https://audioldm.github.io/audioldm2
authors	Haohe Liu; Yi Yuan; Xubo Liu; Xinhao Mei; Qiuqiang Kong; Qiao Tian; Yuping Wang; Wenwu Wang; Yuxuan Wang; Mark D. Plumbley
methods	benchmark evaluation; diffusion modeling; self-supervised learning
code urls	unknown
demo urls	https://audioldm.github.io/audioldm2
exact title	AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining
project urls	https://audioldm.github.io/audioldm2
original title	unknown
citation counts	unknown
research topics	audio generation; evaluation benchmark; music/audio representation learning; text-to-audio generation; 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	unknown
publication or preprint date	2023-08-10
abstract level neutral summary	The work studies audio generation, evaluation benchmark; methods and evaluation details are in the official abstract.
datasets benchmarks models tools used	AudioLDM
correction withdrawal retraction status	No withdrawal marker observed in captured arXiv metadata.