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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The reliability of using fully convolutional networks (FCNs) has beensuccessfully demonstrated by recent studies in many speech applications. One ofthe most popular variants of these FCNs is the `U-Net', which is anencoder-decoder network with skip connections. In this study, we propose`SkipConvNet' where we replace each skip connection with multiple convolutionalmodules to provide decoder with intuitive feature maps rather than encoder'soutput to improve the learning capacity of the network. We also propose the useof optimal smoothing of power spectral density (PSD) as a pre-processing step,which helps to further enhance the efficiency of the network. To evaluate ourproposed system, we use the REVERB challenge corpus to assess the performanceof various enhancement approaches under the same conditions. We focus solely onmonitoring improvements in speech quality and their contribution to improvingthe efficiency of back-end speech systems, such as speech recognition andspeaker verification, trained on only clean speech. Experimental findings showthat the proposed system consistently outperforms other approaches.

SkipConvNet: Skip Convolutional Neural Network for Speech Dereverberation using Optimally Smoothed Spectral Mapping