Subspace Hybrid Beamforming for Head-worn Microphone Arrays

TL;DR

This paper introduces a novel two-stage multi-channel speech enhancement method using adaptive hybrid beamforming and PCA-based denoising, significantly improving noise suppression and speech intelligibility for head-worn microphone arrays.

Contribution

It proposes a new hybrid MVDR beamformer combined with spectral PCA denoising, enhancing robustness and performance over existing methods.

Findings

Outperforms baseline superdirective beamformer in noise suppression metrics.

Improves speech intelligibility (STOI) significantly.

Maintains similar speech quality (PESQ) as baseline.

Abstract

A two-stage multi-channel speech enhancement method is proposed which consists of a novel adaptive beamformer, Hybrid Minimum Variance Distortionless Response (MVDR), Isotropic-MVDR (Iso), and a novel multi-channel spectral Principal Components Analysis (PCA) denoising. In the first stage, the Hybrid-MVDR performs multiple MVDRs using a dictionary of pre-defined noise field models and picks the minimum-power outcome, which benefits from the robustness of signal-independent beamforming and the performance of adaptive beamforming. In the second stage, the outcomes of Hybrid and Iso are jointly used in a two-channel PCA-based denoising to remove the 'musical noise' produced by Hybrid beamformer. On a dataset of real 'cocktail-party' recordings with head-worn array, the proposed method outperforms the baseline superdirective beamformer in noise suppression (fwSegSNR, SDR, SIR, SAR) and speech intelligibility (STOI) with similar speech quality (PESQ) improvement.