Blind Separation of Convolutive Speech Mixtures with Post-Processing Based on Multichannel Signal Enhancement

LIU Jian-qiang; FENG Da-zheng; ZHOU Yi

您当前的位置：

首页 >

文章列表页 >

Blind Separation of Convolutive Speech Mixtures with Post-Processing Based on Multichannel Signal Enhancement

更新时间：2025-07-16

- Blind Separation of Convolutive Speech Mixtures with Post-Processing Based on Multichannel Signal Enhancement
- Acta Electronica Sinica Vol. 35, Issue 12, Pages: 2389-2393(2007)
- 作者机构：
  
  西安电子科技大学雷达信号处理国家重点实验室,陕西,西安,710071
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN911.7
- Published：2007
- 稿件说明：
移动端阅览
LIU Jian-qiang, FENG Da-zheng, ZHOU Yi. Blind Separation of Convolutive Speech Mixtures with Post-Processing Based on Multichannel Signal Enhancement[J]. Acta Electronica Sinica, 2007, 35(12): 2389-2393.
DOI：

LIU Jian-qiang, FENG Da-zheng, ZHOU Yi. Blind Separation of Convolutive Speech Mixtures with Post-Processing Based on Multichannel Signal Enhancement[J]. Acta Electronica Sinica, 2007, 35(12): 2389-2393. DOI：

摘要

由于频域盲源分离方法无法精确解决排列模糊问题

分离出的信号质量受到很大影响.本文提出一种后处理方法以进一步消除不同信源间的空间干扰和噪声且无需增加额外的先验信息.首先在频域盲分离方法中利用分裂语谱技术把一个

M×N

的多输入多输出(MIMO)混迭系统分裂成

个单输入多输出(SIMO)系统

再对每个SIMO系统分别利用传递函数比和广义旁瓣相消器来重构源信号.仿真实验表明该算法具有良好的性能.

Abstract

Due to the imprecision for solving the permutation ambiguity problem

the frequency domain methods for convolutive blind separation have their fundamental limitations in separation quality.Without additional priori information

a post-processing approach is proposed to further attenuate spatial interference from competing sources and noise.Firstly

M×N

multiple-input multiple-output (MIMO) system is converted into

single-input multiple-output (SIMO) systems by splitting spectrogram technique

and then the transfer functions ratios and generalized sidelobe canceller are employed to reconstruct source signals from the

SIMO systems respectively.The performance of the proposed algorithm is demonstrated by computer simutation results.

关键词

Keywords

references

Views

682

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

An In-Vehicle Interaction Speech Enhancement and Recognition Method Based on Lightweight Models in Complex Environment

Suppression Method of the Interference Sound Sources by Estimated Steering Vector Based on the Focusing Signal Subspace

MAP Estimation for Noisy Speech Enhancement Based on Inter-Frame Correlation

Related Author

LIAN Xiao-yu

XIA Nan

DAI Gao-le

YANG Hong-qin

ZHANG Xu

BAO Chang-chun

ZHOU Jing

BAO Chang-chun

Related Institution

School of Information Science and Engineering， Dalian Ploytechnic University

Speech and Audio Signal Processing Laboratory, Faculty of Information Technology, Beijing University of Technology

Speech and Audio Signal Processing Laboratory, School of Electronic Information and Control Engineering, Beijing University of Technology

Laboratory of Information Science,College of Communication Engineering,Jilin University

College of Telecommunications EngineeringXidian UniversityXi'anShaanxi 710071China

⁰