A new multilayer graph model for speech signals with graph learning

This paper investigates the graph representation for speech signals and proposes a novel multilayer graph topology for capturing both the inter-frame and intra-frame relationships among speech samples. Specifically, we use the graph learning method to investigate a graph topology of inter-frames and the graph structure for speech samples within a frame by applying the graph shift operation. On this basis, we define a joint graph Fourier basis by our joint graph adjacency matrix's singular eigenvectors, and further propose a novel vertex-frequency graph Wiener filtering (VFGWF) method, which applies it to improve the speech enhancement performance. Our numerical simulation results show that the designed graph representation can capture the intrinsic relationships between speech frames as well as the relationships among speech samples within a frame. Moreover, compared to the existed graph Wiener filtering method by relying on the graph shift operator and the classical baseline Wiener filtering method, the proposed VFGWF performs better in terms of both average SSNR and PESQ results.& nbsp;(C) 2021 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).