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

Adversarial loss in a conditional generative adversarial network (GAN) is notdesigned to directly optimize evaluation metrics of a target task, and thus,may not always guide the generator in a GAN to generate data with improvedmetric scores. To overcome this issue, we propose a novel MetricGAN approachwith an aim to optimize the generator with respect to one or multipleevaluation metrics. Moreover, based on MetricGAN, the metric scores of thegenerated data can also be arbitrarily specified by users. We tested theproposed MetricGAN on a speech enhancement task, which is particularly suitableto verify the proposed approach because there are multiple metrics measuringdifferent aspects of speech signals. Moreover, these metrics are generallycomplex and could not be fully optimized by Lp or conventional adversariallosses.

MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement