Instantaneous PSD Estimation for Speech Enhancement based on Generalized Principal Components

TL;DR

This paper introduces a novel method for speech enhancement that estimates power spectral density instantaneously using generalized principal components, leading to improved performance over traditional smooth PSD estimation methods.

Contribution

The paper proposes a new instantaneous PSD estimation technique based on generalized principal components, enhancing speech enhancement by capturing time-varying spectral information.

Findings

Instantaneous PSD estimates outperform smooth estimates in speech enhancement.

Simulation shows improved speech quality with the proposed method.

Method provides real-time PSD estimation using generalized eigenvalues.

Abstract

Power spectral density (PSD) estimates of various microphone signal components are essential to many speech enhancement procedures. As speech is highly non-nonstationary, performance improvements may be gained by maintaining time-variations in PSD estimates. In this paper, we propose an instantaneous PSD estimation approach based on generalized principal components. Similarly to other eigenspace-based PSD estimation approaches, we rely on recursive averaging in order to obtain a microphone signal correlation matrix estimate to be decomposed. However, instead of estimating the PSDs directly from the temporally smooth generalized eigenvalues of this matrix, yielding temporally smooth PSD estimates, we propose to estimate the PSDs from newly defined instantaneous generalized eigenvalues, yielding instantaneous PSD estimates. The instantaneous generalized eigenvalues are defined from the generalized principal components, i.e. a generalized eigenvector-based transform of the microphone signals. We further show that the smooth generalized eigenvalues can be understood as a recursive average of the instantaneous generalized eigenvalues. Simulation results comparing the multi-channel Wiener filter (MWF) with smooth and instantaneous PSD estimates indicate better speech enhancement performance for the latter. A MATLAB implementation is available online.