English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In recent years, the burgeoning interest in diffusion models has led tosignificant advances in image and speech generation. Nevertheless, the directsynthesis of music waveforms from unrestricted textual prompts remains arelatively underexplored domain. In response to this lacuna, this paperintroduces a pioneering contribution in the form of a text-to-waveform musicgeneration model, underpinned by the utilization of diffusion models. Ourmethodology hinges on the innovative incorporation of free-form textual promptsas conditional factors to guide the waveform generation process within thediffusion model framework. Addressing the challenge of limited text-musicparallel data, we undertake the creation of a dataset by harnessing webresources, a task facilitated by weak supervision techniques. Furthermore, arigorous empirical inquiry is undertaken to contrast the efficacy of twodistinct prompt formats for text conditioning, namely, music tags andunconstrained textual descriptions. The outcomes of this comparative analysisaffirm the superior performance of our proposed model in terms of enhancingtext-music relevance. Finally, our work culminates in a demonstrativeexhibition of the excellent capabilities of our model in text-to-musicgeneration. We further demonstrate that our generated music in the waveformdomain outperforms previous works by a large margin in terms of diversity,quality, and text-music relevance.

ERNIE-Music: Text-to-Waveform Music Generation with Diffusion Models