HyBeam: Hybrid Microphone-Beamforming Array-Agnostic Speech Enhancement for Wearables

TL;DR

HyBeam is a hybrid speech enhancement framework that combines raw microphone signals and beamformer outputs to achieve robust, array-agnostic performance across diverse acoustic environments and wearable device configurations.

Contribution

It introduces a novel hybrid approach that leverages the strengths of both raw microphone signals and beamformer outputs for array-agnostic speech enhancement.

Findings

HyBeam outperforms baseline methods in PESQ, STOI, and SI-SDR.

Bandwise analysis shows effective use of beamformer at high frequencies and microphone cues at low frequencies.

Demonstrates robustness across diverse room and wearable array configurations.

Abstract

Speech enhancement is a fundamental challenge in signal processing, particularly when robustness is required across diverse acoustic conditions and microphone setups. Deep learning methods have been successful for speech enhancement, but often assume fixed array geometries, limiting their use in mobile, embedded, and wearable devices. Existing array-agnostic approaches typically rely on either raw microphone signals or beamformer outputs, but both have drawbacks under changing geometries. We introduce HyBeam, a hybrid framework that uses raw microphone signals at low frequencies and beamformer signals at higher frequencies, exploiting their complementary strengths while remaining highly array-agnostic. Simulations across diverse rooms and wearable array configurations demonstrate that HyBeam consistently surpasses microphone-only and beamformer-only baselines in PESQ, STOI, and SI-SDR. A bandwise analysis shows that the hybrid approach leverages beamformer directivity at high frequencies and microphone cues at low frequencies, outperforming either method alone across all bands.