Integrated Speech Enhancement Method Based on Weighted Prediction Error and DNN for Dereverberation and Denoising

TL;DR

This paper proposes an integrated speech enhancement method combining WPE and DNN to improve dereverberation and denoising, achieving faster processing and better speech quality.

Contribution

It introduces a novel integration of DNN with WPE to address noise influence and eliminate iterative processing, enhancing efficiency and effectiveness.

Findings

Significant improvement in speech quality.

Faster processing compared to traditional WPE.

Effective noise suppression and dereverberation.

Abstract

Both reverberation and additive noises degrade the speech quality and intelligibility. Weighted prediction error (WPE) method performs well on the dereverberation but with limitations. First, WPE doesn't consider the influence of the additive noise which degrades the performance of dereverberation. Second, it relies on a time-consuming iterative process, and there is no guarantee or a widely accepted criterion on its convergence. In this paper, we integrate deep neural network (DNN) into WPE for dereverberation and denoising. DNN is used to suppress the background noise to meet the noise-free assumption of WPE. Meanwhile, DNN is applied to directly predict spectral variance of the target speech to make the WPE work without iteration. The experimental results show that the proposed method has a significant improvement in speech quality and runs fast.