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

TL;DR

This paper introduces a novel speech dereverberation framework that combines weighted prediction error with plug-and-play data priors, improving performance and robustness in noisy environments.

Contribution

It integrates data-driven speech priors into the WPE method using a plug-and-play strategy, enhancing dereverberation effectiveness.

Findings

Improved dereverberation performance in noisy conditions

Enhanced robustness over traditional WPE methods

Effective incorporation of learned speech priors

Abstract

Speech dereverberation aims to alleviate the detrimental effects of late-reverberant components. While the weighted prediction error (WPE) method has shown superior performance in dereverberation, there is still room for further improvement in terms of performance and robustness in complex and noisy environments. Recent research has highlighted the effectiveness of integrating physics-based and data-driven methods, enhancing the performance of various signal processing tasks while maintaining interpretability. Motivated by these advancements, this paper presents a novel dereverberation frame-work, which incorporates data-driven methods for capturing speech priors within the WPE framework. The plug-and-play strategy (PnP), specifically the regularization by denoising (RED) strategy, is utilized to incorporate speech prior information learnt from data during the optimization problem solving iterations. Experimental results validate the effectiveness of the proposed approach.