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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ilan, Yuval Bar, Rafaely, Boaz, Tourbabin, Vladimir
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911233749286912
author Ilan, Yuval Bar
Rafaely, Boaz
Tourbabin, Vladimir
author_facet Ilan, Yuval Bar
Rafaely, Boaz
Tourbabin, Vladimir
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22637
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HyBeam: Hybrid Microphone-Beamforming Array-Agnostic Speech Enhancement for Wearables
Ilan, Yuval Bar
Rafaely, Boaz
Tourbabin, Vladimir
Audio and Speech Processing
Signal Processing
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.
title HyBeam: Hybrid Microphone-Beamforming Array-Agnostic Speech Enhancement for Wearables
topic Audio and Speech Processing
Signal Processing
url https://arxiv.org/abs/2510.22637