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

Controllable timbre synthesis has been a subject of research for severaldecades, and deep neural networks have been the most successful in this area.Deep generative models such as Variational Autoencoders (VAEs) have the abilityto generate a high-level representation of audio while providing a structuredlatent space. Despite their advantages, the interpretability of these latentspaces in terms of human perception is often limited. To address thislimitation and enhance the control over timbre generation, we propose aregularized VAE-based latent space that incorporates timbre descriptors.Moreover, we suggest a more concise representation of sound by utilizing itsharmonic content, in order to minimize the dimensionality of the latent space.

Interpretable Timbre Synthesis using Variational Autoencoders Regularized on Timbre Descriptors