An Iterative Graph Spectral Subtraction Method for Speech Enhancement

TL;DR

This paper introduces an iterative graph spectral subtraction method for speech enhancement using graph signal processing, demonstrating improved noise suppression and speech quality over traditional methods.

Contribution

The paper proposes a novel iterative graph spectral subtraction (IGSS) method based on graph signal processing for enhanced speech noise reduction.

Findings

IGSS outperforms BSS and IBSS in SNR.

Proposed operators are effective for graph speech signals.

Enhanced speech quality demonstrated through PESQ improvements.

Abstract

In this paper, we investigate the application of graph signal processing (GSP) theory in speech enhancement. We first propose a set of shift operators to construct graph speech signals, and then analyze their spectrum in the graph Fourier domain. By leveraging the differences between the spectrum of graph speech and graph noise signals, we further propose the graph spectral subtraction (GSS) method to suppress the noise interference in noisy speech. Moreover, based on GSS, we propose the iterative graph spectral subtraction (IGSS) method to further improve the speech enhancement performance. Our experimental results show that the proposed operators are suitable for graph speech signals, and the proposed methods outperform the traditional basic spectral subtraction (BSS) method and iterative basic spectral subtraction (IBSS) method in terms of both signal-to-noise ratios (SNR) and mean Perceptual Evaluation of Speech Quality (PESQ).