Speech Enhancement with Dual-path Multi-Channel Linear Prediction Filter and Multi-norm Beamforming

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qin, Chengyuan, Xiong, Wenmeng, Zhou, Jing, Jia, Maoshen, Bao, Changchun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918103444619264
author Qin, Chengyuan
Xiong, Wenmeng
Zhou, Jing
Jia, Maoshen
Bao, Changchun
author_facet Qin, Chengyuan
Xiong, Wenmeng
Zhou, Jing
Jia, Maoshen
Bao, Changchun
contents In this paper, we propose a speech enhancement method us ing dual-path Multi-Channel Linear Prediction (MCLP) filters and multi-norm beamforming. Specifically, the MCLP part in the proposed method is designed with dual-path filters in both time and frequency dimensions. For the beamforming part, we minimize the power of the microphone array output as well as the l1 norm of the denoised signals while preserving source sig nals from the target directions. An efficient method to select the prediction orders in the dual-path filters is also proposed, which is robust for signals with different reverberation time (T60) val ues and can be applied to other MCLP-based methods. Eval uations demonstrate that our proposed method outperforms the baseline methods for speech enhancement, particularly in high reverberation scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18350
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Speech Enhancement with Dual-path Multi-Channel Linear Prediction Filter and Multi-norm Beamforming
Qin, Chengyuan
Xiong, Wenmeng
Zhou, Jing
Jia, Maoshen
Bao, Changchun
Audio and Speech Processing
Sound
In this paper, we propose a speech enhancement method us ing dual-path Multi-Channel Linear Prediction (MCLP) filters and multi-norm beamforming. Specifically, the MCLP part in the proposed method is designed with dual-path filters in both time and frequency dimensions. For the beamforming part, we minimize the power of the microphone array output as well as the l1 norm of the denoised signals while preserving source sig nals from the target directions. An efficient method to select the prediction orders in the dual-path filters is also proposed, which is robust for signals with different reverberation time (T60) val ues and can be applied to other MCLP-based methods. Eval uations demonstrate that our proposed method outperforms the baseline methods for speech enhancement, particularly in high reverberation scenarios.
title Speech Enhancement with Dual-path Multi-Channel Linear Prediction Filter and Multi-norm Beamforming
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2507.18350