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

We describe our approach for the generative emotional vocal burst task (ExVoGenerate) of the ICML Expressive Vocalizations Competition. We train aconditional StyleGAN2 architecture on mel-spectrograms of preprocessed versionsof the audio samples. The mel-spectrograms generated by the model are theninverted back to the audio domain. As a result, our generated samplessubstantially improve upon the baseline provided by the competition from aqualitative and quantitative perspective for all emotions. More precisely, evenfor our worst-performing emotion (awe), we obtain an FAD of 1.76 compared tothe baseline of 4.81 (as a reference, the FAD between the train/validation setsfor awe is 0.776).

Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms