eduzhai > Applied Sciences > Engineering >

An Iterative Graph Spectral Subtraction Method for Speech Enhancement

  • Save

... pages left unread,continue reading

Document pages: 22 pages

Abstract: In this paper, we investigate the application of graph signal processing(GSP) theory in speech enhancement. We first propose a set of shift operatorsto construct graph speech signals, and then analyze their spectrum in the graphFourier domain. By leveraging the differences between the spectrum of graphspeech and graph noise signals, we further propose the graph spectralsubtraction (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. Ourexperimental results show that the proposed operators are suitable for graphspeech signals, and the proposed methods outperform the traditional basicspectral subtraction (BSS) method and iterative basic spectral subtraction(IBSS) method in terms of both signal-to-noise ratios (SNR) and mean PerceptualEvaluation of Speech Quality (PESQ).

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×