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

Speech dereverberation aims to alleviate the detrimental effects oflate-reverberant components. While the weighted prediction error (WPE) methodhas shown superior performance in dereverberation, there is still room forfurther improvement in terms of performance and robustness in complex and noisyenvironments. Recent research has highlighted the effectiveness of integratingphysics-based and data-driven methods, enhancing the performance of varioussignal processing tasks while maintaining interpretability. Motivated by theseadvancements, this paper presents a novel dereverberation frame-work, whichincorporates data-driven methods for capturing speech priors within the WPEframework. The plug-and-play strategy (PnP), specifically the regularization bydenoising (RED) strategy, is utilized to incorporate speech prior informationlearnt from data during the optimization problem solving iterations.Experimental results validate the effectiveness of the proposed approach.

Integrating Plug-and-Play Data Priors with Weighted Prediction Error for Speech Dereverberation