结合脉冲响应重塑和期望最大化的盲信号分离

解元; 张旭; 邹涛; 马鸽; 余锦视; 孙为军

doi:10.12263/DZXB.20230272

您当前的位置：

首页 >

文章列表页 >

结合脉冲响应重塑和期望最大化的盲信号分离

学术论文 | 更新时间：2025-12-08

- 结合脉冲响应重塑和期望最大化的盲信号分离
- Blind Signal Separation Combining Impulse Response Remodeling and Expectation Maximization
- 电子学报 2023年51卷第11期页码：3343-3353
- 作者机构：
  
  1.广州大学机械与电气工程学院,广东广州 510006
  2.智能检测与制造物联教育部重点实验室,广东广州 510006
  3.粤港澳复杂制造多尺度信息融合与协同优化控制重点验室,广东广州 510006
  4.广州市制造过程综合自动化重点实验室,广东广州 510006
  5.广东省物联网信息技术重点实验室,广东广州 510006
  6.物联网智能信息处理与系统集成教育部重点实验室,广东广州 510006
- 作者简介：
  
  [ "解元男，1989年出生于安徽利辛县.现为广州大学机械与电气工程学院讲师、硕士生导师.主要研究方向为盲信号分离、信号处理和机器学习等.E-mail: xieyuan@gzhu.edu.cn" ]
  [ "张旭男，2000年出生于广东韶关市.现为广州大学机械与电气工程学院硕士研究生. 主要研究方向为盲信号分离.E-mail: sgzx8480@e.gzhu.cn" ]
  [ "邹涛（通讯作者）男，1975年出生于辽宁营口.现为广州大学机械与电气工程学院教授、博士生导师.主要研究方向为工业过程建模与仿真、模型预测控制、先进过程控制和实时优化技术研究与应用." ]
  [ "马鸽女，1988年出生于山东济宁.广州大学机械与电气工程学院副教授、硕士生导师.主要研究方向为图像处理、机器视觉、控制理论与应用等.E-mail: m_ge@gzhu.edu.cn" ]
  [ "余锦视男，1990年出生于广东潮汕市.现为广州大学机械与电气工程学院博士后.主要研究包括非负矩阵分解、张量分解、张量完成和机器学习等.E-mail: jinshi.yu@gzhu.edu.cn" ]
  [ "孙为军男，1975年出生于安徽马鞍山市.现为广东工业大学自动化学院副教授、硕士生导师.主要研究方向为模式识别、机器学习等.E-mail: gdutswj@163.com" ]
- 基金信息：
  
  广州市基础与应用基础研究项目(SL2022A04J00289);广东省基础与应用基础研究基金(2023A1515011311);国家自然科学基金(62003095;52171331);广州市市校联合实验室项目(2023A03J0120)
- DOI：10.12263/DZXB.20230272
  中图分类号： TN912.3;
- 收稿：2023-03-28，
  
  修回：2023-05-04，
  
  纸质出版：2023-11-25
- 稿件说明：
移动端阅览
解元,张旭,邹涛等.结合脉冲响应重塑和期望最大化的盲信号分离[J].电子学报,2023,51(11):3343-3353.

XIE Yuan,ZHANG Xu,ZOU Tao,et al.Blind Signal Separation Combining Impulse Response Remodeling and Expectation Maximization[J].ACTA ELECTRONICA SINICA,2023,51(11):3343-3353.
解元,张旭,邹涛等.结合脉冲响应重塑和期望最大化的盲信号分离[J].电子学报,2023,51(11):3343-3353. DOI： 10.12263/DZXB.20230272.

XIE Yuan,ZHANG Xu,ZOU Tao,et al.Blind Signal Separation Combining Impulse Response Remodeling and Expectation Maximization[J].ACTA ELECTRONICA SINICA,2023,51(11):3343-3353. DOI： 10.12263/DZXB.20230272.

摘要

多通道欠定卷积语音混合信号的分离问题是盲信号分离领域的难点.由于混合信号中常伴随声学回声和混响，真实的源信号很难完全被清晰地分离出来.传统的盲信号分离算法多数适用于低混响，而在高混响场景下，算法的分离性能极速下降甚至是失效的.本文针对具有声学回声和混响环境下的多通道欠定卷积语音混合信号的分离问题，提出一种结合脉冲响应重塑和期望最大化的盲信号分离算法，该算法在低混响和高混响下都表现出很好的分离性能.首先，利用基于无穷范数和

范数的脉冲响应重塑技术设计预滤波器消除可听回声，完成对混合信号的重塑，提高混合信号的质量.然后，对重塑后的混合信号利用分层聚类方法估计混合矩阵，基于期望最大化算法框架，设计新的模型参数实时更新规则，通过结合脉冲响应重塑和期望最大化重构源信号.实验结果表明，所提算法可以有效地分离不同混响环境下带声学回声的欠定卷积混合信号，其分离性能优越，同时对噪声具有很好的鲁棒性.

Abstract

The separation of multichannel underdetermined convolutive speech mixing signals is a difficult problem in the field of blind signal separation. Due to the acoustic echo and reverberation in the mixing signals

it is difficult to completely and clearly separate the real source signals. Most traditional blind signal separation algorithms are suitable for low reverberation

while in high reverberation scenarios

the separation performance of the algorithm rapidly degrades or even fails. To separate multichannel convolutive mixing signals with acoustic echo and reverberation

a blind signal separation algorithm is proposed combining impulse response remodeling and expectation maximization

which exhibits good separation performance in both low and high reverberation environments. Firstly

a pre-filter is designed using impulse response remodeling technology based on infinite and

-norm to eliminate audible echoes

remodeling the

room impulse response and improving the quality of the mixing signals. Then

a hierarchical clustering method is used to estimate the mixing matrix for the remodeled mixing signals

the new model parameters real-time update rules are designed based on expectation maximization algorithm framework

and the source signals are reconstructed combining the impulse response remodeling and expectation maximization. Experimental results show that the proposed algorithm can effectively separate the speech mixing signals with acoustic echoes in different reverberation environments

owning superior separation performance and good robustness to noise.

关键词

Keywords

references

BEE M A , MICHEYL C . The cocktail party problem: What is it? How can it be solved? And why should animal behaviorists study it? [J ] . Journal of Comparative Psychology , 2008 , 122 ( 3 ): 235 - 251 .

WOODS K J P , MCDERMOTT J H . Schema learning for the cocktail party problem [J ] . Proceedings of the National Academy of Sciences of the United States of America , 2018 , 115 ( 14 ): E3313 - E3322 .

JUTTEN C , HERAULT J . Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture [J ] . Signal Processing , 1991 , 24 ( 1 ): 1 - 10 .

皮磊 , 朱磊 , 郑翔 , 等 . 基于改进Wave-U-Net跳跃连接的盲源分离算法 [J ] . 信号处理 , 2022 , 38 ( 4 ): 835 - 843 .

PI L , ZHU L , ZHENG X , et al . Blind source separation algorithm based on improved wave-U-net skip connection [J ] . Journal of Signal Processing , 2022 , 38 ( 4 ): 835 - 843 . (in Chinese)

XIE Y , XIE K , YANG Q Y , et al . Reverberant blind separation of heart and lung sounds using nonnegative matrix factorization and auxiliary function technique [J ] . Biomedical Signal Processing and Control , 2021 , 69 : 102899 .

刘秋红 , 许漫坤 , 李天昀 , 等 . 基于互补对称滤波器的APCMA信号的盲分离算法 [J ] . 电子学报 , 2020 , 48 ( 12 ): 2394 - 2401 .

LIU Q H , XU M K , LI T Y , et al . Blind separation of APCMA signal based on complementary symmetric filters [J ] . Acta Electronica Sinica , 2020 , 48 ( 12 ): 2394 - 2401 . (in Chinese)

李帅 , 刘宏清 , 彭鹏 , 等 . 混响环境下基于卷积模型的欠定盲源分离 [J ] . 信号处理 , 2021 , 37 ( 4 ): 624 - 632 .

LI S , LIU H Q , PENG P , et al . Underdetermined blind source separation based on convolution model in reverberant environment [J ] . Journal of Signal Processing , 2021 , 37 ( 4 ): 624 - 632 . (in Chinese)

SHI Y H , ZENG W M , WANG N Z , et al . A new constrained spatiotemporal ICA method based on multi-objective optimization for fMRI data analysis [J ] . IEEE Transactions on Neural Systems and Rehabilitation Engineering , 2018 , 26 ( 9 ): 1690 - 1699 .

田宝平 , 应昊蓉 , 杨文境 , 等 . 结合ICA和复数神经网络的双麦阵列盲源分离方法 [J ] . 信号处理 , 2021 , 37 ( 11 ): 2185 - 2192 .

TIAN B P , YING H R , YANG W J , et al . Blind source separation of binary array based on ICA and complex neural network [J ] . Journal of Signal Processing , 2021 , 37 ( 11 ): 2185 - 2192 . (in Chinese)

FENG F C , KOWALSKI M . Revisiting sparse ICA from a synthesis point of view: Blind Source Separation for over and underdetermined mixtures [J ] . Signal Processing , 2018 , 152 : 165 - 177 .

GEORGIEV P , THEIS F , CICHOCKI A . Sparse component analysis and blind source separation of underdetermined mixtures [J ] . IEEE Transactions on Neural Networks , 2005 , 16 ( 4 ): 992 - 996 .

XIE Y , XIE K , XIE S L . Underdetermined blind source separation of speech mixtures unifying dictionary learning and sparse representation [J ] . International Journal of Machine Learning and Cybernetics , 2021 , 12 ( 12 ): 3573 - 3583 .

DUONG N Q K , VINCENT E , GRIBONVAL R . Under-determined reverberant audio source separation using a full-rank spatial covariance model [J ] . IEEE Transactions on Audio, Speech, and Language Processing , 2010 , 18 ( 7 ): 1830 - 1840 .

FENG F C , KOWALSKI M . Underdetermined reverberant blind source separation: Sparse approaches for multiplicative and convolutive narrowband approximation [J ] . IEEE/ACM Transactions on Audio, Speech, and Language Processing , 2019 , 27 ( 2 ): 442 - 456 .

GUO J Y , LIU S , YU K , et al . An ultrahigh voltage shunt reactor acoustic signal separation method based on masking beamforming and underdetermined blind source separation [J ] . IEEE Transactions on Instrumentation and Measurement , 2023 , 72 : 1 - 8 .

NION D , MOKIOS K N , SIDIROPOULOS N D , et al . Batch and adaptive PARAFAC-based blind separation of convolutive speech mixtures [J ] . IEEE Transactions on Audio, Speech, and Language Processing , 2010 , 18 ( 6 ): 1193 - 1207 .

QIN G D , AMIN M G , ZHANG Y D . DOA estimation exploiting sparse array motions [J ] . IEEE Transactions on Signal Processing , 2019 , 67 ( 11 ): 3013 - 3027 .

SAWADA H , MUKAI R , ARAKI S , et al . A robust and precise method for solving the permutation problem of frequency-domain blind source separation [J ] . IEEE Transactions on Speech and Audio Processing , 2004 , 12 ( 5 ): 530 - 538 .

SU Q , ZHANG X W , SHA N , et al . Underdetermined blind direction-of-arrival estimation using a moving platform [J ] . IEEE Signal Processing Letters , 2022 , 29 : 2532 - 2536 .

马宝泽 , 张天骐 , 安泽亮 , 等 . 基于张量分解的卷积盲源分离方法 [J ] . 通信学报 , 2021 , 42 ( 8 ): 52 - 60 .

MA B Z , ZHANG T Q , AN Z L , et al . Convolutive blind source separation method based on tensor decomposition [J ] . Journal on Communications , 2021 , 42 ( 8 ): 52 - 60 . (in Chinese)

XIE K , ZHOU G X , YANG J J , et al . Eliminating the permutation ambiguity of convolutive blind source separation by using coupled frequency bins [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2020 , 31 ( 2 ): 589 - 599 .

MA B Z , LI G J , YI C . Tensor-based underdetermined blind identification of instantaneous mixtures [J ] . IEEE Transactions on Circuits and Systems II: Express Briefs , 2023 , 70 ( 1 ): 346 - 350 .

LEE D D , SEUNG H S . Learning the parts of objects by non-negative matrix factorization [J ] . Nature , 1999 , 401 ( 6755 ): 788 - 791 .

解元 , 邹涛 , 孙为军 , 等 . 面向卷积混叠环境下的盲源分离新方法 [J ] . 自动化学报 , 2023 , 49 ( 5 ): 1062 - 1072 .

XIE Y , ZOU T , SUN W J , et al . Novel blind source separation method for convolutive mixed environment [J ] . Acta Automatica Sinica , 2023 , 49 ( 5 ): 1062 - 1072 . (in Chinese)

WANG T H , YANG F R , YANG J . Convolutive transfer function-based multichannel nonnegative matrix factorization for overdetermined blind source separation [J ] . IEEE/ACM Transactions on Audio, Speech, and Language Processing , 2022 , 30 : 802 - 815 .

刘升东 , 杨飞然 , 杨军 . 基于最小体积约束的频域卷积盲源分离 [J ] . 信号处理 , 2023 , 39 ( 5 ): 829 - 836 .

LIU S D , YANG F R , YANG J . Frequency-domain convolutive blind source separation with minimum volume constraint [J ] . Journal of Signal Processing , 2023 , 39 ( 5 ): 829 - 836 . (in Chinese)

KOUNADES-BASTIAN D , GIRIN L , ALAMEDA-PINEDA X , et al . A variational EM algorithm for the separation of time-varying convolutive audio mixtures [J ] . IEEE/ACM Transactions on Audio, Speech, and Language Processing , 2016 , 24 ( 8 ): 1408 - 1423 .

AL-TMEME A , WOO W L , DLAY S S , et al . Underdetermined convolutive source separation using GEM-MU with variational approximated optimum model order NMF2D [J ] . IEEE/ACM Transactions on Audio, Speech, and Language Processing , 2017 , 25 ( 1 ): 35 - 49 .

XIE Y , XIE K , XIE S L . Underdetermined convolutive blind separation of sources integrating tensor factorization and expectation maximization [J ] . Digital Signal Processing , 2019 , 87 : 145 - 154 .

XIE K , JIANG K Y , YANG Q Y . Multi-channel underdetermined blind source separation for recorded audio mixture signals using an unmanned aerial vehicle [J ] . IET Communications , 2021 , 15 ( 10 ): 1412 - 1422 .

MERTINS A , MEI T M , KALLINGER M . Room impulse response shortening/reshaping with infinity and p -norm optimization [J ] . IEEE Transactions on Audio, Speech, and Language Processing , 2010 , 18 ( 2 ): 249 - 259 .

DAU T , KOLLMEIER B , KOHLRAUSCH A . Modeling auditory processing of amplitude modulation. I. Detection and masking with narrow-band carriers [J ] . The Journal of the Acoustical Society of America , 1997 , 102 ( 5 ): 2892 - 2905 .

WINTER S , KELLERMANN W , SAWADA H , et al . MAP-based underdetermined blind source separation of convolutive mixtures by hierarchical clustering and-norm minimization [J ] . EURASIP Journal on Advances in Signal Processing , 2007 : 024717 .

VINCENT E , GRIBONVAL R , FEVOTTE C . Performance measurement in blind audio source separation [J ] . IEEE Transactions on Audio, Speech, and Language Processing , 2006 , 14 ( 4 ): 1462 - 1469 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于随机退化数据建模的设备剩余寿命自适应预测方法

基于合并分层聚类的网络拓扑推断算法

自适应类别的层次高斯混合模型遥感影像分割