# Multi-Channel Speech Enhancement using Graph Neural Networks

arXiv: https://arxiv.org/abs/2102.06934 · HTML: https://mlsanity.com/paper/2102.06934/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2021.

## Built on by (most cited first, 5 of 5)

- [Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data](https://mlsanity.com/paper/2202.00097/) (2022)
- [Implicit Neural Spatial Filtering for Multichannel Source Separation in the Waveform Domain](https://mlsanity.com/paper/2206.15423/) (2022)
- [Activation Compression of Graph Neural Networks using Block-wise Quantization with Improved Variance Minimization](https://mlsanity.com/paper/2309.11856/) (2023)
- [Deep Neural Mel-Subband Beamformer for In-car Speech Separation](https://mlsanity.com/paper/2211.12590/) (2022)
- [RelUNet: Relative Channel Fusion U-Net for Multichannel Speech Enhancement](https://mlsanity.com/paper/2410.05019/) (2024)

## Abstract (arXiv)

Multi-channel speech enhancement aims to extract clean speech from a noisy mixture using signals captured from multiple microphones. Recently proposed methods tackle this problem by incorporating deep neural network models with spatial filtering techniques such as the minimum variance distortionless response (MVDR) beamformer. In this paper, we introduce a different research direction by viewing each audio channel as a node lying in a non-Euclidean space and, specifically, a graph. This formulation allows us to apply graph neural networks (GNN) to find spatial correlations among the different channels (nodes). We utilize graph convolution networks (GCN) by incorporating them in the embedding space of a U-Net architecture. We use LibriSpeech dataset and simulate room acoustics data to extensively experiment with our approach using different array types, and number of microphones. Results indicate the superiority of our approach when compared to prior state-of-the-art method.