en
×

分享给微信好友或者朋友圈

使用微信“扫一扫”功能。
作者简介:

吴礼福,男,博士,副教授,研究方向为音频信号处理.wulifu@nuist.edu.cn

中图分类号:TN912

文献标识码:A

DOI:10.13878/j.cnki.jnuist.20220222001

参考文献 1
张琦,王霞,王磊,等.自适应回波抵消中变步长NLMS算法[J].数据采集与处理,2013,28(1):64-68 ZHANG Qi,WANG Xia,WANG Lei,et al.Variable step-size NLMS algorithms in echo cancellation[J].Journal of Data Acquisition & Processing,2013,28(1):64-68
参考文献 2
Morgan D R,Kratzer S G.On a class of computationally efficient,rapidly converging,generalized NLMS algorithms[J].IEEE Signal Processing Letters,1996,3(8):245-247
参考文献 3
Albu I,Anghel C,Paleologu C.Adaptive filtering in acoustic echo cancellation systems:a practical overview[C]//2017 9th International Conference on Electronics,Computers and Artificial Intelligence(ECAI).June 29-July 1,2017,Targoviste,Romania.IEEE,2017:1-6
参考文献 4
Valin J M.On adjusting the learning rate in frequency domain echo cancellation with double-talk[J].IEEE Transactions on Audio,Speech,and Language Processing,2007,15(3):1030-1034
参考文献 5
Yang J.Multilayer adaptation based complex echo cancellation and voice enhancement[C]//2018 IEEE International Conference on Acoustics,Speech and Signal Processing.April 15-20,2018,Calgary,AB,Canada.IEEE,2018:2131-2135
参考文献 6
丁锋.辅助模型辨识方法(5):最小二乘辨识[J].南京信息工程大学学报(自然科学版),2016,8(5):385-403 DING Feng.Auxiliary model based identification methods.Part E:least squares identification[J].Journal of Nanjing University of Information Science & Technology(Natural Science Edition),2016,8(5):385-403
参考文献 7
杨果,王亚洁,王晶.Speex编码器中回声消除算法的分析与评估[J].电声技术,2013,37(9):52-55 YANG Guo,WANG Yajie,WANG Jing.Analysis and evaluation of echo cancellation algorithm in speex codec[J].Audio Engineering,2013,37(9):52-55
参考文献 8
Ono N,Miyabe S.Auxiliary-function-based independent component analysis for super-Gaussian sources[C]//Latent Variable Analysis and Signal Separation,2010:165-172
参考文献 9
Gunther J.Learning echo paths during continuous double-talk using semi-blind source separation[J].IEEE Transactions on Audio,Speech,and Language Processing,2012,20(2):646-660
参考文献 10
Ikram M Z.Blind source separation and acoustic echo cancellation:a unified framework[C]//2012 IEEE International Conference on Acoustics,Speech and Signal Processing.March 25-30,2012,Kyoto,Japan.IEEE,2012:1701-1704
参考文献 11
张艳萍,李杰.回波对消中盲源分离算法的研究与仿真[J].南京信息工程大学学报(自然科学版),2013,5(6):539-543 ZHANG Yanping,LI Jie.Optimization and simulation of blind source separation in acoustic echo cancellation[J].Journal of Nanjing University of Information Science & Technology(Natural Science Edition),2013,5(6):539-543
参考文献 12
石怀涛,周乾,王雨桐,等.基于相对变换的ICA故障检测方法[J].电子测量与仪器学报,2017,31(7):1040-1046 SHI Huaitao,ZHOU Qian,WANG Yutong,et al.Fault detection method based on relative-transformation ICA[J].Journal of Electronic Measurement and Instrumentation,2017,31(7):1040-1046
参考文献 13
Scheibler R,Ono N.Independent vector analysis with more microphones than sources[C]//2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics.October 20-23,2019,New Paltz,NY,USA.IEEE,2019:185-189
参考文献 14
Lei Q H,Chen H,Hou J F,et al.Deep neural network based regression approach for acoustic echo cancellation[C]//Proceedings of the 2019 4th International Conference on Multimedia Systems and Signal Processing.2019:94-98
参考文献 15
周晓彦,王珂,李凌燕.基于深度学习的目标检测算法综述[J].电子测量技术,2017,40(11):89-93 ZHOU Xiaoyan,WANG Ke,LI Lingyan.Review of object detection based on deep learning[J].Electronic Measurement Technology,2017,40(11):89-93
参考文献 16
Taniguchi T,Ono N,Kawamura A,et al.An auxiliary-function approach to online independent vector analysis for real-time blind source separation[C]//2014 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays(HSCMA).May 12-14,2014,Villers-les-Nancy,France.IEEE,2014:107-111
参考文献 17
Ono N.Auxiliary-function-based independent vector analysis with power of vector-norm type weighting functions[C]//Proceedings of the 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference.December 3-6,2012,Hollywood,CA,USA.IEEE,2012:1-4
参考文献 18
魏本征,甘洁,尹义龙.基于边缘特征点互信息熵的医学图像配准方法[J].数据采集与处理,2018,33(2):248-258 WEI Benzheng,GAN Jie,YIN Yilong.Medical image registration based on mutual information entropy combined with edge correlation feature[J].Journal of Data Acquisition and Processing,2018,33(2):248-258
参考文献 19
姜波,杨军,张尔扬.稀疏自适应Volterra滤波的QRD-RLS算法[J].信号处理,2008,24(4):595-599 JIANG Bo,YANG Jun,ZHANG Eryang.QRD-RLS algorithm for sparse adaptive Volterra filtering[J].Signal Processing,2008,24(4):595-599
参考文献 20
Allen J B,Berkley D A.Image method for efficiently simulating small-room acoustics[J].The Journal of the Acoustical Society of America,1979,65(4):943-950
参考文献 21
Loizou P C.Speech enhancement:theory and practice[M].Florida:CRC Press,2007:492-495
目录contents

    摘要

    传统的声回波消除(Acoustic Echo Cancellation,AEC)方法使用双端通话检测器判断单、双端通话场景,性能受限.盲源分离(Blind Source Separation,BSS)信号模型是一个远端和近端信号并存的全双工模型,因此基于BSS的AEC无需双端通话检测器.本文采用基于辅助函数的独立分量分析(Auxiliary function based Independent Component Analysis,Aux-ICA)算法在频域上实现声回波消除,以最小化互信息为目标函数,借助辅助函数技术进行优化.仿真实验结果表明,在连续的双端通话场景中,该方法具有较低的计算复杂度和较好的回波消除性能.

    Abstract

    The performance of traditional Acoustic Echo Cancellation (AEC) is restricted due to the double-talk detector it used to determine the double-talk and single-talk scenarios.While Blind Source Separation (BSS) signal model is a full duplex model with both far-end and near-end signals,thus the BSS-based AEC does not need the double-talk detector.This paper adopts Auxiliary function based Independent Component Analysis (Aux-ICA) algorithm to realize acoustic echo cancellation in frequency domain,in which the object function is minimizing the mutual information,and the auxiliary function technique is used for optimization.Simulation results show that this method has lower computational complexity and better performance in acoustic echo cancellation under continuous double-talk scenarios.

  • 0 引言

  • 在网络会议、免提通话等应用中,都不同程度地存在声回波问题.回波的存在影响通信质量,严重时会使通信系统不能正常工作.因此,必须采取有效措施来抑制回波,消除其影响.回波消除是通常采用的一种方法,其基本思想是估计出回波路径,得出回波信号的估计,从传声器信号中减去该估计信号,实现回波消除.

  • 自适应滤波[1]是声回波消除的常用方法之一.归一化最小均方(Normalized Least Mean Square,NLMS)算法[2-3]是回波消除的典型算法,该算法通过梯度下降法使估计的回波与麦克风信号之间的均方误差最小.为了防止滤波器发散,需要额外使用双端通话检测器(Double-Talk Detector,DTD)[4]或自适应步长策略[5]来减缓或停止双端通话时自适应滤波器的调整.递归最小二乘法(Recursive Least Square,RLS)[6]也是一种AEC算法,与NLMS算法相比,RLS算法具有更快的收敛速度,但其计算复杂度也更高.Speex MDF[7]是一种广泛使用的自适应滤波回声消除算法,它以NLMS算法为基础,用频域多延时(Multi Delay block Frequency domain,MDF)滤波算法实现,推导出最优步长估计,其优点是滤波器系数基于块更新.

  • 前述的AEC方法存在一定的不足.基于梯度下降的方法存在收敛速度与稳定性之间的平衡问题[8].尽管DTD和自适应步长策略在单向通话和偶尔发生的双端通话场景中都能很好地工作,但在连续双端通话场景中,近端信号总是存在,它们的性能可能会下降[9].盲源分离[10-11]是一种从观测到的混合信号中分离出期望信号来实现信号分离或增强的技术.独立分量分析(Independent Component Analysis,ICA)[12]和独立矢量分析(Independent Vector Analysis,IVA)[13]是典型的BSS技术.AEC可以被认为是一个半盲源分离问题,其目标是从传声器(麦克风)信号中分离出回波和近端信号.

  • 近年来,基于深度学习(Deep Learning)[14-15]的回波消除方法虽然展示了很好的性能,但是这种数据驱动方法主要有两个不足:一是需要足够的数据进行训练,目前虽然有一些开源音频数据库,但这些数据库通常不足以建立鲁棒的神经网络; 二是深度神经网络的参数无法解释,这对于希望从自己的需求出发来操纵和调整回波消除系统性能的工程师或实际用户来说是无法接受的.

  • 与传统的AEC算法相比,由于BSS信号模型是一个远端和近端信号并存的全双工模型,所以基于BSS的AEC算法在连续双端通话场景中具有更好的回波消除能力.同时,Speex MDF算法的优异性能表明频域实现AEC具有一定的优势.因而本文采用基于辅助函数的独立分量分析在频域实现声回波消除,在全双工特性的基础上,利用辅助函数技术,避免了显式步长参数选择,降低了算法的计算复杂度.

  • 1 问题描述

  • 1.1 信号模型

  • 不考虑非线性回波,本文使用的信号模型如图1所示.麦克风信号x由线性回波e和近端信号s两部分组成:

  • x=s+e.
    (1)
  • 图1 信号模型

  • Fig.1 Signal model

  • 若系统中只存在一个参考信号r,则线性回波e可以看作参考信号r和未知的回波路径a的卷积,如式(2)所示,*表示线性卷积.

  • e=a*r.
    (2)
  • 如图1中的虚线框所示,AEC通过参考信号r和估计的回波路径b计算出回波估计.之后从x中减去得到信号y,也就是估计的近端信号.如式(3)和式(4)所示:

  • e^=b*r
    (3)
  • y=x-e^
    (4)
  • 经过短时傅里叶变换后,时域信号可以转换为式(5)和式(6)中的频域信号模型:

  • X(τ)=S(τ)+A(τ)R(τ),
    (5)
  • Y(τ)=X(τ)-B(τ)R(τ),
    (6)
  • 其中,τ是帧索引,XS,R,Y,A,B分别表示频域中的麦克风信号、近端信号、参考信号、估计的近端信号、未知的回波路径和估计的回波路径.

  • 1.2 BSS模型

  • 式(5)和式(6)中的信号模型也可以表示为式(7)和式(8)中的BSS混合和分离模型,L为滤波器的阶数,()H表示共轭转置.

  • X(τ)RH(τ)=1A1(τ),,AL(τ)0L×1IL×LE(τ)S(τ)RH(τ),
    (7)
  • Y(τ)RH(τ)=1B1(τ),,BL(τ)0L×1IL×LF(τ)X(τ)RH(τ),
    (8)
  • 其中,0为零矩阵,I为单位矩阵,矩阵E为混合矩阵,矩阵F为分离矩阵.与传统的AEC算法不同,BSS可以被看作为远端和近端信号共存的全双工模型,S作为BSS信号模型中的独立分量.

  • 2 Aux-ICA算法

  • 2.1 算法推导

  • 根据Aux-ICA算法[816],首先通过式(10)中的非线性β更新加权相关矩阵C[17],如式(9)和式(10)所示.其中γ是稀疏参数,α是遗忘因子,δ是防止分母为零而设置的一个很小的数.

  • C(τ)=αC(τ-1)+β(τ)X(τ)XH(τ),
    (9)
  • β(τ)=(1-α)Y(τ)2+δ(γ-2)/2
    (10)
  • 分离滤波器w=FHi1=[1,BT]T可根据式(11)和式(12)计算,i1=[1,0,···,0]TL+1维向量,()T表示转置.与盲源分离问题不同,基于BSS的AEC中不存在模糊性问题.因此,w根据式(12)进行归一化,以确保分离矩阵F保持式(8)中的结构.

  • w (τ) =[F (τ-1) C (τ) ]-1i1=

  • C-1(τ)F-1(τ-1)i1,
    (11)
  • ww/w1
    (12)
  • 由式(8)可以看出,分离矩阵F是对角线元素为1、第一行元素为非零元素、其他元素为0的上三角矩阵,所以F-1与分离矩阵F有着相同的结构.又因为i1=[1,0,···,0]T,所以式(11)中矩阵的计算仅与C-1F-1的第一列元素有关,因此在式(11)中避免了分离矩阵F的求逆过程,如式(13)所示:

  • w(τ)=C-1(τ)i1
    (13)
  • 因此分离滤波器w可以写成式(14)的形式:

  • w=1,BTT=C-1i1
    (14)
  • 式(9)和式(11)中的相关矩阵C可以转换为式(15)到式(18)的表现形式,其中V是参考信号的自相关矩阵,P是麦克风信号和参考信号的互相关矩阵.

  • C=C11PHPV,
    (15)
  • C11(τ)=αC11(τ-1)+β(τ)X(τ)XH(τ),
    (16)
  • P(τ)=αP(τ-1)+β(τ)R(τ)XH(τ),
    (17)
  • V(τ)=αV(τ-1)+β(τ)R(τ)RH(τ)
    (18)
  • 根据分块矩阵的求逆,C-1可以表示为式(19)的形式:

  • C-1=1C11-PHV-1P-PHC11V-PPHC11-V-1PC11-PHV-1PV-PPHC11-1.
    (19)
  • 将式(19)代入式(14),可以得到如式(20)所示的解:

  • 1BT=1C11-PHV-1P-V-1PC11-PHV-1P
    (20)
  • 将式(20)化简得到如式(21)所示的简化解:

  • B(τ)=V-1(τ)P(τ)
    (21)
  • 因为式(8)中的BSS分离模型可以解释为向麦克风信号添加负回波估计,所以式(20)到式(21)中的负号可以省略,不用像传统AEC模型那样减去它.

  • 2.2 讨论

  • Aux-ICA AEC的目标函数是通过最小化互信息得到的,互信息由KL散度(Kullback-Leibler divergence)测量[18],并由辅助函数技术进行优化.在ICA模型中,近端信号被明确地建模为一个独立分量,ICA中的非线性参数β作为加权值.非线性参数β的使用,提高了语音的分离性能.又因为BSS信号模型是远端和近端信号共存的全双工模型,所以Aux-ICA AEC在连续双端通话场景中具有良好的回波消除能力.由于式(21)包含矩阵求逆,计算量较大,并不适合在线应用,可以使用QRD-RLS(QR Decomposition-RLS)算法[19]降低计算复杂度.

  • 在频域进行信号处理时,为防止由于第1帧的回波路径为零矩阵而在信号前端产生较大误差,仿真中需对麦克风信号的第1帧进行预处理,即对第1帧的所有点按照本文算法进行迭代,使得第1帧的回波路径为非全零矩阵.其余帧再根据第1帧进行迭代.Aux-ICA AEC算法消除回波的流程如表1所示.

  • 表1 Aux-ICA AEC算法

  • Table1 The Aux-ICA AEC algorithm

  • 3 仿真实验

  • 3.1 实验环境

  • 仿真中建立了一个5 m×7 m×2.4 m的房间,随机模拟声源和麦克风的位置以及方向.房间脉冲响应(Room Impulse Response,RIR)根据镜像源方法产生[20].从采样率为16 kHz的100组声源和参考信号的数据集中随机选出一组信号,其时长约为24 s.参考信号包含音乐和语音两种类型(即回波信号可以是音乐或语音),在实验过程中始终存在,以模拟连续的双端通话场景.根据式(1)和式(2),参考信号与模拟的回声路径进行卷积,然后根据信号回波比(Signal to Echo Radio,SER)进行混合,得到实验数据.在本实验中比较了两种算法:Speex MDF和Aux-ICA AEC.其中Speex MDF算法的滤波器长度设置为512,帧长设置为256.Aux-ICA AEC算法中,短时傅里叶变换的长度为8 192,帧移为4 096.本文通过设置不同的混响时间(RT60,表示从声音突然停止到声压级降低 60 dB 所用的时间)和信号回波比(SER)的数值,进行多次实验.使用同样硬件平台下算法运行时间T来比较不同算法的计算复杂度,利用语音质量感知评价(Perceptual Evaluation of Speech Quality,PESQ)[21]评估回波消除后的近端语音质量.实验的仿真参数设置如表2所示.

  • 表2 仿真环境参数设置

  • Table2 Simulation environment parameters setting

  • 3.2 结果和讨论

  • 表3和表4显示了在不同程度混响环境(RT60=0.2 s、0.4 s、0.8 s)下的连续双端通话场景中,回波信号分别为音乐和语音时,SER取不同的值时所得的算法运行时间.

  • 表3、4中,TAux表示Aux-ICA AEC算法的运行时间,TSpeex表示Speex MDF算法的运行时间.由表3和表4可以观察到,在相同程度混响环境下的连续双端通话场景中,SER取值相同的情况下,回波信号为音乐时,Aux-ICA AEC算法的运行时间比Speex MDF算法的运行时间平均低了约6.87%,回波信号为语音时,Aux-ICA AEC算法的运行时间比Speex MDF算法的运行时间平均低了约11.91%,这说明了Aux-ICA AEC算法具有更低的计算复杂度.相比于Speex MDF算法,Aux-ICA AEC算法基于BSS的全双工特性,不需要额外使用DTD,因此Aux-ICA AEC算法具有更低的计算复杂度,仿真实验也验证了这一点.

  • 本文采用PESQ对实验中回波消除后的信号进行评估,如图2—7所示(其中图2—4是回波为音乐时的实验结果,图5—7是回波为语音时的实验结果),PESQ得分越高,表示算法的回波消除能力越好.从图2和图5中可以看出,当RT60=0.2 s,SER=10 dB,相比于RT60=0.2 s,SER=-10 dB时,由于回波幅值的减小,Aux-ICA AEC算法具有更高的PESQ得分.随着混响程度的加剧,图4中RT60=0.8 s,SER=-10 dB,相比于图2中RT60=0.2 s,SER=-10 dB时,Aux-ICA AEC算法的回波消除能力下降,但其回波消除性能仍明显优于Speex MDF算法.

  • 从图2—7的各组数据中可以看出,在相同的连续双端通话场景中,Speex MDF算法的PESQ得分均低于Aux-ICA AEC算法的PESQ得分,这验证了Aux-ICA AEC算法在连续双端通话场景中具有更好的回波消除性能.

  • 图2 RT60为0.2 s时算法的PESQ得分(回波信号为音乐)

  • Fig.2 PESQ score of the algorithm when RT60 is 0.2 s (the echo signal is music)

  • 表3 回波信号为音乐时不同程度混响环境下的算法运行时间

  • Table3 Algorithm running time in different degrees of reverberation environment when echo signal is music

  • 表4 回波信号为语音时不同程度混响环境下的算法运行时间

  • Table4 Algorithm running time in different degrees of reverberation environment when echo signal is voice

  • 图3 RT60为0.4 s时算法的PESQ得分(回波信号为音乐)

  • Fig.3 PESQ score of the algorithm when RT60 is 0.4 s (the echo signal is music)

  • 图4 RT60为0.8 s时算法的PESQ得分(回波信号为音乐)

  • Fig.4 PESQ score of the algorithm when RT60 is 0.8 s (the echo signal is music)

  • 图5 RT60为0.2 s时算法的PESQ得分(回波信号为语音)

  • Fig.5 PESQ score of the algorithm when RT60 is 0.2 s (the echo signal is voice)

  • 图6 RT60为0.4 s时算法的PESQ得分(回波信号为语音)

  • Fig.6 PESQ score of the algorithm when RT60 is 0.4 s (the echo signal is voice)

  • 图7 RT60为0.8 s时算法的PESQ得分(回波信号为语音)

  • Fig.7 PESQ score of the algorithm when RT60 is 0.8 s (the echo signal is voice)

  • 4 结论

  • 本文研究了一种基于辅助函数的ICA算法,在频域上实现声回波消除.在全双工特性的基础上,利用辅助函数技术,可以省略显式步长参数选择和双端通话检测器,降低了算法的计算复杂度.仿真验证了该方法具有更低的计算复杂度以及更好的回波消除性能.

  • 参考文献

    • [1] 张琦,王霞,王磊,等.自适应回波抵消中变步长NLMS算法[J].数据采集与处理,2013,28(1):64-68 ZHANG Qi,WANG Xia,WANG Lei,et al.Variable step-size NLMS algorithms in echo cancellation[J].Journal of Data Acquisition & Processing,2013,28(1):64-68

    • [2] Morgan D R,Kratzer S G.On a class of computationally efficient,rapidly converging,generalized NLMS algorithms[J].IEEE Signal Processing Letters,1996,3(8):245-247

    • [3] Albu I,Anghel C,Paleologu C.Adaptive filtering in acoustic echo cancellation systems:a practical overview[C]//2017 9th International Conference on Electronics,Computers and Artificial Intelligence(ECAI).June 29-July 1,2017,Targoviste,Romania.IEEE,2017:1-6

    • [4] Valin J M.On adjusting the learning rate in frequency domain echo cancellation with double-talk[J].IEEE Transactions on Audio,Speech,and Language Processing,2007,15(3):1030-1034

    • [5] Yang J.Multilayer adaptation based complex echo cancellation and voice enhancement[C]//2018 IEEE International Conference on Acoustics,Speech and Signal Processing.April 15-20,2018,Calgary,AB,Canada.IEEE,2018:2131-2135

    • [6] 丁锋.辅助模型辨识方法(5):最小二乘辨识[J].南京信息工程大学学报(自然科学版),2016,8(5):385-403 DING Feng.Auxiliary model based identification methods.Part E:least squares identification[J].Journal of Nanjing University of Information Science & Technology(Natural Science Edition),2016,8(5):385-403

    • [7] 杨果,王亚洁,王晶.Speex编码器中回声消除算法的分析与评估[J].电声技术,2013,37(9):52-55 YANG Guo,WANG Yajie,WANG Jing.Analysis and evaluation of echo cancellation algorithm in speex codec[J].Audio Engineering,2013,37(9):52-55

    • [8] Ono N,Miyabe S.Auxiliary-function-based independent component analysis for super-Gaussian sources[C]//Latent Variable Analysis and Signal Separation,2010:165-172

    • [9] Gunther J.Learning echo paths during continuous double-talk using semi-blind source separation[J].IEEE Transactions on Audio,Speech,and Language Processing,2012,20(2):646-660

    • [10] Ikram M Z.Blind source separation and acoustic echo cancellation:a unified framework[C]//2012 IEEE International Conference on Acoustics,Speech and Signal Processing.March 25-30,2012,Kyoto,Japan.IEEE,2012:1701-1704

    • [11] 张艳萍,李杰.回波对消中盲源分离算法的研究与仿真[J].南京信息工程大学学报(自然科学版),2013,5(6):539-543 ZHANG Yanping,LI Jie.Optimization and simulation of blind source separation in acoustic echo cancellation[J].Journal of Nanjing University of Information Science & Technology(Natural Science Edition),2013,5(6):539-543

    • [12] 石怀涛,周乾,王雨桐,等.基于相对变换的ICA故障检测方法[J].电子测量与仪器学报,2017,31(7):1040-1046 SHI Huaitao,ZHOU Qian,WANG Yutong,et al.Fault detection method based on relative-transformation ICA[J].Journal of Electronic Measurement and Instrumentation,2017,31(7):1040-1046

    • [13] Scheibler R,Ono N.Independent vector analysis with more microphones than sources[C]//2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics.October 20-23,2019,New Paltz,NY,USA.IEEE,2019:185-189

    • [14] Lei Q H,Chen H,Hou J F,et al.Deep neural network based regression approach for acoustic echo cancellation[C]//Proceedings of the 2019 4th International Conference on Multimedia Systems and Signal Processing.2019:94-98

    • [15] 周晓彦,王珂,李凌燕.基于深度学习的目标检测算法综述[J].电子测量技术,2017,40(11):89-93 ZHOU Xiaoyan,WANG Ke,LI Lingyan.Review of object detection based on deep learning[J].Electronic Measurement Technology,2017,40(11):89-93

    • [16] Taniguchi T,Ono N,Kawamura A,et al.An auxiliary-function approach to online independent vector analysis for real-time blind source separation[C]//2014 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays(HSCMA).May 12-14,2014,Villers-les-Nancy,France.IEEE,2014:107-111

    • [17] Ono N.Auxiliary-function-based independent vector analysis with power of vector-norm type weighting functions[C]//Proceedings of the 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference.December 3-6,2012,Hollywood,CA,USA.IEEE,2012:1-4

    • [18] 魏本征,甘洁,尹义龙.基于边缘特征点互信息熵的医学图像配准方法[J].数据采集与处理,2018,33(2):248-258 WEI Benzheng,GAN Jie,YIN Yilong.Medical image registration based on mutual information entropy combined with edge correlation feature[J].Journal of Data Acquisition and Processing,2018,33(2):248-258

    • [19] 姜波,杨军,张尔扬.稀疏自适应Volterra滤波的QRD-RLS算法[J].信号处理,2008,24(4):595-599 JIANG Bo,YANG Jun,ZHANG Eryang.QRD-RLS algorithm for sparse adaptive Volterra filtering[J].Signal Processing,2008,24(4):595-599

    • [20] Allen J B,Berkley D A.Image method for efficiently simulating small-room acoustics[J].The Journal of the Acoustical Society of America,1979,65(4):943-950

    • [21] Loizou P C.Speech enhancement:theory and practice[M].Florida:CRC Press,2007:492-495

  • 参考文献

    • [1] 张琦,王霞,王磊,等.自适应回波抵消中变步长NLMS算法[J].数据采集与处理,2013,28(1):64-68 ZHANG Qi,WANG Xia,WANG Lei,et al.Variable step-size NLMS algorithms in echo cancellation[J].Journal of Data Acquisition & Processing,2013,28(1):64-68

    • [2] Morgan D R,Kratzer S G.On a class of computationally efficient,rapidly converging,generalized NLMS algorithms[J].IEEE Signal Processing Letters,1996,3(8):245-247

    • [3] Albu I,Anghel C,Paleologu C.Adaptive filtering in acoustic echo cancellation systems:a practical overview[C]//2017 9th International Conference on Electronics,Computers and Artificial Intelligence(ECAI).June 29-July 1,2017,Targoviste,Romania.IEEE,2017:1-6

    • [4] Valin J M.On adjusting the learning rate in frequency domain echo cancellation with double-talk[J].IEEE Transactions on Audio,Speech,and Language Processing,2007,15(3):1030-1034

    • [5] Yang J.Multilayer adaptation based complex echo cancellation and voice enhancement[C]//2018 IEEE International Conference on Acoustics,Speech and Signal Processing.April 15-20,2018,Calgary,AB,Canada.IEEE,2018:2131-2135

    • [6] 丁锋.辅助模型辨识方法(5):最小二乘辨识[J].南京信息工程大学学报(自然科学版),2016,8(5):385-403 DING Feng.Auxiliary model based identification methods.Part E:least squares identification[J].Journal of Nanjing University of Information Science & Technology(Natural Science Edition),2016,8(5):385-403

    • [7] 杨果,王亚洁,王晶.Speex编码器中回声消除算法的分析与评估[J].电声技术,2013,37(9):52-55 YANG Guo,WANG Yajie,WANG Jing.Analysis and evaluation of echo cancellation algorithm in speex codec[J].Audio Engineering,2013,37(9):52-55

    • [8] Ono N,Miyabe S.Auxiliary-function-based independent component analysis for super-Gaussian sources[C]//Latent Variable Analysis and Signal Separation,2010:165-172

    • [9] Gunther J.Learning echo paths during continuous double-talk using semi-blind source separation[J].IEEE Transactions on Audio,Speech,and Language Processing,2012,20(2):646-660

    • [10] Ikram M Z.Blind source separation and acoustic echo cancellation:a unified framework[C]//2012 IEEE International Conference on Acoustics,Speech and Signal Processing.March 25-30,2012,Kyoto,Japan.IEEE,2012:1701-1704

    • [11] 张艳萍,李杰.回波对消中盲源分离算法的研究与仿真[J].南京信息工程大学学报(自然科学版),2013,5(6):539-543 ZHANG Yanping,LI Jie.Optimization and simulation of blind source separation in acoustic echo cancellation[J].Journal of Nanjing University of Information Science & Technology(Natural Science Edition),2013,5(6):539-543

    • [12] 石怀涛,周乾,王雨桐,等.基于相对变换的ICA故障检测方法[J].电子测量与仪器学报,2017,31(7):1040-1046 SHI Huaitao,ZHOU Qian,WANG Yutong,et al.Fault detection method based on relative-transformation ICA[J].Journal of Electronic Measurement and Instrumentation,2017,31(7):1040-1046

    • [13] Scheibler R,Ono N.Independent vector analysis with more microphones than sources[C]//2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics.October 20-23,2019,New Paltz,NY,USA.IEEE,2019:185-189

    • [14] Lei Q H,Chen H,Hou J F,et al.Deep neural network based regression approach for acoustic echo cancellation[C]//Proceedings of the 2019 4th International Conference on Multimedia Systems and Signal Processing.2019:94-98

    • [15] 周晓彦,王珂,李凌燕.基于深度学习的目标检测算法综述[J].电子测量技术,2017,40(11):89-93 ZHOU Xiaoyan,WANG Ke,LI Lingyan.Review of object detection based on deep learning[J].Electronic Measurement Technology,2017,40(11):89-93

    • [16] Taniguchi T,Ono N,Kawamura A,et al.An auxiliary-function approach to online independent vector analysis for real-time blind source separation[C]//2014 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays(HSCMA).May 12-14,2014,Villers-les-Nancy,France.IEEE,2014:107-111

    • [17] Ono N.Auxiliary-function-based independent vector analysis with power of vector-norm type weighting functions[C]//Proceedings of the 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference.December 3-6,2012,Hollywood,CA,USA.IEEE,2012:1-4

    • [18] 魏本征,甘洁,尹义龙.基于边缘特征点互信息熵的医学图像配准方法[J].数据采集与处理,2018,33(2):248-258 WEI Benzheng,GAN Jie,YIN Yilong.Medical image registration based on mutual information entropy combined with edge correlation feature[J].Journal of Data Acquisition and Processing,2018,33(2):248-258

    • [19] 姜波,杨军,张尔扬.稀疏自适应Volterra滤波的QRD-RLS算法[J].信号处理,2008,24(4):595-599 JIANG Bo,YANG Jun,ZHANG Eryang.QRD-RLS algorithm for sparse adaptive Volterra filtering[J].Signal Processing,2008,24(4):595-599

    • [20] Allen J B,Berkley D A.Image method for efficiently simulating small-room acoustics[J].The Journal of the Acoustical Society of America,1979,65(4):943-950

    • [21] Loizou P C.Speech enhancement:theory and practice[M].Florida:CRC Press,2007:492-495

  • 地址:江苏省南京市宁六路219号    邮编:210044

    联系电话:025-58731025    E-mail:nxdxb@nuist.edu.cn

    南京信息工程大学学报 ® 2024 版权所有  技术支持:北京勤云科技发展有限公司