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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Generative Adversarial Networks (GANs) have achieved excellent audiosynthesis quality in the last years. However, making them operable withsemantically meaningful controls remains an open challenge. An obvious approachis to control the GAN by conditioning it on metadata contained in audiodatasets. Unfortunately, audio datasets often lack the desired annotations,especially in the musical domain. A way to circumvent this lack of annotationsis to generate them, for example, with an automatic audio-tagging system. Theoutput probabilities of such systems (so-called "soft labels") carry richinformation about the characteristics of the respective audios and can be usedto distill the knowledge from a teacher model into a student model. In thiswork, we perform knowledge distillation from a large audio tagging system intoan adversarial audio synthesizer that we call DarkGAN. Results show thatDarkGAN can synthesize musical audio with acceptable quality and exhibitsmoderate attribute control even with out-of-distribution input conditioning. Werelease the code and provide audio examples on the accompanying website.

DarkGAN: Exploiting Knowledge Distillation for Comprehensible Audio Synthesis with GANs