AudioLDM: Text-to-Audio Generation with Latent Diffusion Models

research work·research paper·active

Research work examining audio generation, music/audio representation learning.

Recorded facts

Official site	https://arxiv.org/abs/2301.12503 ↗
Geography	Global
arxiv	2301.12503
venue	Accepted by ICML 2023. Demo and implementation at https://audioldm.github.io. Evaluation toolbox at https://github.com/haoheliu/audioldm_eval
authors	Haohe Liu; Zehua Chen; Yi Yuan; Xinhao Mei; Xubo Liu; Danilo Mandic; Wenwu Wang; Mark D. Plumbley
methods	contrastive learning; diffusion modeling
code urls	https://github.com/haoheliu/audioldm_eval
demo urls	https://audioldm.github.io; https://github.com/haoheliu/audioldm_eval
exact title	AudioLDM: Text-to-Audio Generation with Latent Diffusion Models
project urls	https://audioldm.github.io
original title	unknown
citation counts	unknown
research topics	audio generation; music/audio representation learning; text-to-audio 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	2023-01-29
abstract level neutral summary	The work studies audio generation, music/audio representation learning; methods and evaluation details are in the official abstract.
datasets benchmarks models tools used	AudioCaps; AudioLDM; CLAP
correction withdrawal retraction status	No withdrawal marker observed in captured arXiv metadata.