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

Synthetic creation of drum sounds (e.g., in drum machines) is commonlyperformed using analog or digital synthesis, allowing a musician to sculpt thedesired timbre modifying various parameters. Typically, such parameters controllow-level features of the sound and often have no musical meaning or perceptualcorrespondence. With the rise of Deep Learning, data-driven processing of audioemerges as an alternative to traditional signal processing. This new paradigmallows controlling the synthesis process through learned high-level features orby conditioning a model on musically relevant information. In this paper, weapply a Generative Adversarial Network to the task of audio synthesis of drumsounds. By conditioning the model on perceptual features computed with apublicly available feature-extractor, intuitive control is gained over thegeneration process. The experiments are carried out on a large collection ofkick, snare, and cymbal sounds. We show that, compared to a specific prior workbased on a U-Net architecture, our approach considerably improves the qualityof the generated drum samples, and that the conditional input indeed shapes theperceptual characteristics of the sounds. Also, we provide audio examples andrelease the code used in our experiments.

DrumGAN: Synthesis of Drum Sounds With Timbral Feature Conditioning Using Generative Adversarial Networks