peerRTF: Robust MVDR Beamforming Using Graph Convolutional Network

TL;DR

This paper introduces peerRTF, a graph convolutional network-based method to robustly estimate relative transfer functions in noisy, reverberant environments, improving microphone array beamforming performance.

Contribution

It presents a novel GCN-based approach to learn the RTF manifold, enhancing robustness in RTF estimation for MVDR beamforming in challenging acoustic conditions.

Findings

Improved RTF estimation accuracy in noisy environments

Enhanced MVDR beamformer performance

Validated on real and simulated data

Abstract

Accurate and reliable identification of the relative transfer functions (RTFs) between microphones with respect to a desired source is an essential component in the design of microphone array beamformers, specifically when applying the minimum variance distortionless response (MVDR) criterion. Since an accurate estimation of the RTF in a noisy and reverberant environment is a cumbersome task, we aim at leveraging prior knowledge of the acoustic enclosure to robustify the RTFs estimation by learning the RTF manifold. In this paper, we present a novel robust RTF identification method, tested and trained using both real recordings and simulated scenarios, which relies on learning the RTF manifold using a graph convolutional network (GCN) to infer a robust representation of the RTFs in a confined area, and consequently enhance the beamformers performance.