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

Generally, the performance of deep neural networks (DNNs) heavily depends onthe quality of data representation learning. Our preliminary work hasemphasized the significance of deep representation learning (DRL) in thecontext of speech enhancement (SE) applications. Specifically, our initial SEalgorithm employed a gated recurrent unit variational autoencoder (VAE) with aGaussian distribution to enhance the performance of certain existing SEsystems. Building upon our preliminary framework, this paper introduces a novelapproach for SE using deep complex convolutional recurrent networks with a VAE(DCCRN-VAE). DCCRN-VAE assumes that the latent variables of signals followcomplex Gaussian distributions that are modeled by DCCRN, as thesedistributions can better capture the behaviors of complex signals.Additionally, we propose the application of a residual loss in DCCRN-VAE tofurther improve the quality of the enhanced speech. {Compared to ourpreliminary work, DCCRN-VAE introduces a more sophisticated DCCRN structure andprobability distribution for DRL. Furthermore, in comparison to DCCRN,DCCRN-VAE employs a more advanced DRL strategy. The experimental resultsdemonstrate that the proposed SE algorithm outperforms both our preliminary SEframework and the state-of-the-art DCCRN SE method in terms of scale-invariantsignal-to-distortion ratio, speech quality, and speech intelligibility.

A Deep Representation Learning-based Speech Enhancement Method Using Complex Convolution Recurrent Variational Autoencoder