Controlling the Parameterized Multi-channel Wiener Filter using a tiny neural network

TL;DR

This paper introduces NeuralPMWF, a low-complexity neural network-controlled multi-channel Wiener filter that balances noise suppression and speech distortion effectively, outperforming several baselines.

Contribution

It proposes a novel system where a tiny neural network fully controls the classical PMWF, combining neural network flexibility with classical signal processing transparency.

Findings

Significantly improved perceptual speech quality.

Outperforms competitive baselines in objective metrics.

Maintains low computational complexity.

Abstract

Noise suppression and speech distortion are two important aspects to be balanced when designing multi-channel Speech Enhancement (SE) algorithms. Although neural network models have achieved state-of-the-art noise suppression, their non-linear operations often introduce high speech distortion. Conversely, classical signal processing algorithms such as the Parameterized Multi-channel Wiener Filter ( PMWF) beamformer offer explicit mechanisms for controlling the suppression/distortion trade-off. In this work, we present NeuralPMWF, a system where the PMWF is entirely controlled using a low-latency, low-compute neural network, resulting in a low-complexity system offering high noise reduction and low speech distortion. Experimental results show that our proposed approach results in significantly better perceptual and objective speech enhancement in comparison to several competitive baselines using similar computational resources.