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 network (GAN) still exists some problems in dealingwith speech enhancement (SE) task. Some GAN-based systems adopt the samestructure from Pixel-to-Pixel directly without special optimization. Theimportance of the generator network has not been fully explored. Other relatedresearches change the generator network but operate in the time-frequencydomain, which ignores the phase mismatch problem. In order to solve theseproblems, a deep complex convolution recurrent GAN (DCCRGAN) structure isproposed in this paper. The complex module builds the correlation betweenmagnitude and phase of the waveform and has been proved to be effective. Theproposed structure is trained in an end-to-end way. Different LSTM layers areused in the generator network to sufficiently explore the speech enhancementperformance of DCCRGAN. The experimental results confirm that the proposedDCCRGAN outperforms the state-of-the-art GAN-based SE systems.

DCCRGAN: Deep Complex Convolution Recurrent Generator Adversarial Network for Speech Enhancement