An Effective Dereverberation Algorithm by Fusing MVDR and MCLP

TL;DR

This paper introduces a novel dereverberation method that combines MVDR beamforming with MCLP, improving parameter estimation and speech clarity in reverberant environments.

Contribution

It proposes a fusion of MVDR and MCLP with a new PSD estimation approach for enhanced dereverberation performance.

Findings

Outperforms existing dereverberation methods in experiments

Accurately estimates PSD of target speech, noise, and reverberation

Improves speech quality in reverberant scenarios

Abstract

In the scenario with reverberation, the experience of human-machine interaction will become worse. In order to solve this problem, many methods for the dereverberation have emerged. At present, how to update the parameters of the Kalman filter in the existing dereverberation methods based on multichannel linear prediction (MCLP) is a challenging task, especially, accurate power spectral density (PSD) estimation of target speech. In this paper, minimum variance distortionless response (MVDR) beamformer and MCLP are effectively fused in the dereverberation, where the PSD of target speech used for Kalman filter is modified in the MCLP. In order to construct a MVDR beamformer, the PSD of late reverberation and the PSD of the noise are estimated simultaneously by the blocking-based PSD estimator. Thus, the PSD of target speech used for Kalman filter can be obtained by subtracting the PSD of late reverberation and the PSD of the noise from the PSD of observation signal. Compared to the reference methods, the proposed method shows an outstanding performance.