An Effective Method for Enhancing Robustness of Generalized Sidelobe Canceller Beamformer in Noisy Recording Scenario

High level of noise, interference or non-directional noise source degrade the perceptual quality, speech intelligibility of received speech. Consequently, improving the recording speech signal is a crucial pre-processing in several applications, such as cochlear implants, smart - home, mobile phone, teleconference system, hearing aids, voice - controlled equipment. Microphone array (MA) technology is typically placed at a distance from a target speaker to capture the original speech component and requires removing background noise, interference or competing talkers. MA beamforming provides high diversity toward the sound source, saving the clean speech data and eliminating background noise. Generalized Sidelobe Canceller (GSC) beamformer is commonly integrated into numerous acoustic applications due to its effective performance in almost all recording scenarios. Because of the moving head of talker during conversation, the difference of microphone quality, the error of estimated steering vector, the microphone mismatches, the displacement of MA, the inaccurate sampling rate, GSC beamformer’s evaluation often decreased. In this contribution, the authors proposed an effective way of controlling the steering vector to improve beamforming’s performance. The obtained results has proven the advantage of the author’s proposed method in improving the robustness of GSC beamformer in complex and adverse recording environments.

Authors

Institutions

Publication Details

Published
2025-09-08
DOI
https://doi.org/10.1109/diped66951.2025.11194490
Primary Topic
Speech and Audio Processing
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

An Effective Method for Enhancing Robustness of Generalized Sidelobe Canceller Beamformer in Noisy Recording Scenario

Quan Trong The, Nguyen Thi Huyen Chau
Speech and Audio Processing
article

An Effective Method for Enhancing Robustness of Generalized Sidelobe Canceller Beamformer in Noisy Recording Scenario

Quan Trong The, Nguyen Thi Huyen Chau
article en

Abstract

High level of noise, interference or non-directional noise source degrade the perceptual quality, speech intelligibility of received speech. Consequently, improving the recording speech signal is a crucial pre-processing in several applications, such as cochlear implants, smart - home, mobile phone, teleconference system, hearing aids, voice - controlled equipment. Microphone array (MA) technology is typically placed at a distance from a target speaker to capture the original speech component and requires removing background noise, interference or competing talkers. MA beamforming provides high diversity toward the sound source, saving the clean speech data and eliminating background noise. Generalized Sidelobe Canceller (GSC) beamformer is commonly integrated into numerous acoustic applications due to its effective performance in almost all recording scenarios. Because of the moving head of talker during conversation, the difference of microphone quality, the error of estimated steering vector, the microphone mismatches, the displacement of MA, the inaccurate sampling rate, GSC beamformer’s evaluation often decreased. In this contribution, the authors proposed an effective way of controlling the steering vector to improve beamforming’s performance. The obtained results has proven the advantage of the author’s proposed method in improving the robustness of GSC beamformer in complex and adverse recording environments.

Thang Long University (VN), Research Institute of Posts and Telecommunications (SK)
Openalex Percentile: Top 64%
Speech and Audio Processing
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.