Distributed speech dereverberation using weighted prediction error

Speech dereverberation aims to alleviate the negative impact of late reverberant components. The weighted prediction error (WPE) method is a well-established technique known for its superior performance in dereverberation. However, in scenarios where microphone nodes are dispersed, the centralized a...

Full description

Saved in:
Bibliographic Details
Published in:Signal processing 2024-12, Vol.225, p.109577, Article 109577
Main Authors: Yang, Ziye, Zhang, Mengfei, Chen, Jie
Format: Article
Language:English
Subjects:
Distributed estimation
Far-field scenario
Speech dereverberation
The weighted prediction error method
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Speech dereverberation aims to alleviate the negative impact of late reverberant components. The weighted prediction error (WPE) method is a well-established technique known for its superior performance in dereverberation. However, in scenarios where microphone nodes are dispersed, the centralized approach of the WPE method requires aggregating all observations for inverse filtering, resulting in a significant computational burden in a single fusion center. This paper introduces a distributed speech dereverberation method that emphasizes low computational complexity at each node. Specifically, we leverage the distributed adaptive node-specific signal estimation (DANSE) algorithm within the multichannel linear prediction (MCLP) process. This approach empowers each node to perform local operations with reduced complexity while achieving the global performance through inter-node cooperation. Experimental results validate the effectiveness of our proposed method, showcasing its ability to achieve efficient speech dereverberation in dispersed microphone node scenarios.
ISSN:0165-1684
DOI:10.1016/j.sigpro.2024.109577