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

There have been several successful deep learning models that perform audiosuper-resolution. Many of these approaches involve using preprocessed featureextraction which requires a lot of domain-specific signal processing knowledgeto implement. Convolutional Neural Networks (CNNs) improved upon this frameworkby automatically learning filters. An example of a convolutional approach isAudioUNet, which takes inspiration from novel methods of upsampling images. Ourpaper compares the pre-upsampling AudioUNet to a new generative model thatupsamples the signal before using deep learning to transform it into a morebelievable signal. Based on the EDSR network for image super-resolution, thenewly proposed model outperforms UNet with a 20% increase in log spectraldistance and a mean opinion score of 4.06 compared to 3.82 for the two timesupsampling case. AudioEDSR also has 87% fewer parameters than AudioUNet. Howincorporating AudioUNet into a Wasserstein GAN (with gradient penalty)(WGAN-GP) structure can affect training is also explored. Finally the effectsartifacting has on the current state of the art is analysed and solutions tothis problem are proposed. The methods used in this paper have broadapplications to telephony, audio recognition and audio generation tasks.

An investigation of pre-upsampling generative modelling and Generative Adversarial Networks in audio super resolution