基于FastICA的低信噪比下L-PLC语音的间断传输

计算机工程与应用 ›› 2016, Vol. 52 ›› Issue (9): 108-111.

基于FastICA的低信噪比下L-PLC语音的间断传输

恩德1，陈亚柯1，毛哲龙2

1.河南理工大学电气工程及其自动化学院，河南焦作 454000
2.河南省鹤壁供电公司，河南鹤壁 458000

出版日期:2016-05-01 发布日期:2016-05-16

Discontinuous transmission of voice in L-PLC under low SNR based on FastICA

EN De1, CHEN Yake1, MAO Zhelong2

1.School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo, Henan 454000, China
2.Hebi Power Supply Corporation, Hebi, Henan 458000, China

Online:2016-05-01 Published:2016-05-16

摘要/Abstract

摘要： 在低压电力线通信（L-PLC）中，多径衰减和信道背景噪声大的问题不可忽视，为此提出了一种基于快速独立分量分析（FastICA）的L-PLC间断传输提升抗干扰能力的方法。在建立L-PLC信道噪声模型的基础上，利用FastICA对强噪声干扰的语音信号进行去噪处理，并对处理后的信号进行话音活性检测，最终获得满足质量要求的语音段。Matlab仿真实验结果表明，在低信噪比环境下，该方法成功实现了有条件的语音信号间断传输，并在一定程度上提高了语音传输质量。

关键词: 快速独立分量分析, 低压电力线通信, 噪声模型, 间断传输, 话音活性检测

Abstract: The problems of multipath attenuation and high background noise in the channel of Low voltage Power Line Communication（L-PLC） system can not be ignored. Discontinuous transmission of L-PLC based on Fast Independent Component Analysis（FastICA） is proposed to improve the anti-jamming ability of system. On the basis of the establishment of noise model of the low voltage power line channel, this paper uses the FastICA to denoise the voice signal having strong noises on the low voltage power line, does voice activity detection for the processed voice signal, and eventually achieves the speech signal which meets certain quality requirements. The Matlab simulation experimental results show that under low SNR, the described method successfully achieves the goal of conditional continuous speech signal transmission, and improves to some extent the quality of the voice transmission.

Key words: Fast Independent Component Analysis（ICA）, Low voltage Power Line Communication（L-PLC）, noise model, discontinuous transmission, voice activity detection

恩德1，陈亚柯1，毛哲龙2. 基于FastICA的低信噪比下L-PLC语音的间断传输[J]. 计算机工程与应用, 2016, 52(9): 108-111.

EN De1, CHEN Yake1, MAO Zhelong2. Discontinuous transmission of voice in L-PLC under low SNR based on FastICA[J]. Computer Engineering and Applications, 2016, 52(9): 108-111.

[1]	何安玲，何选森. 基于有理非线性函数的Fast-ICA算法[J]. 计算机工程与应用, 2018, 54(1): 251-255.
[2]	陈梦，何选森. 基于八阶收敛牛顿迭代的Fast-ICA改进算法[J]. 计算机工程与应用, 2017, 53(11): 178-181.
[3]	罗文娟1，袁莉芬1，2，何怡刚2. 一种基于十五阶的FastICA改进算法[J]. 计算机工程与应用, 2016, 52(20): 108-113.
[4]	蔡伟华，何选森. 基于UWT和独立分量分析的含噪盲源分离[J]. 计算机工程与应用, 2016, 52(16): 180-185.
[5]	汪道德1，何鹏举1，龙莉莉2. FSS-kernel与FastICA融合的盲源分离算法研究[J]. 计算机工程与应用, 2015, 51(2): 209-212.
[6]	邓昌建1，2，陈东义1，张衡3，胡红阳1，凌建中1. 工业无线网络Krylov子空间估计与动态信道选择[J]. 计算机工程与应用, 2015, 51(11): 62-66.
[7]	王振朝，张士兵. DCSK的反相叠加相关解调方案[J]. 计算机工程与应用, 2011, 47(15): 145-147.
[8]	刘伯权，曾以成，邬鑫锋. 独立分量分析与时频掩蔽结合的语音盲分离[J]. 计算机工程与应用, 2010, 46(32): 130-132.
[9]	胡爱凤，黎明，李军华. 噪声环境下遗传算法的研究[J]. 计算机工程与应用, 2009, 45(27): 46-49.
[10]	李营,艾玲梅. 基于独立分量分析的脑电信号的眼电伪迹消除[J]. 计算机工程与应用, 2009, 45(15): 209-212.
[11]	谢松云,张伟平,潘辉. ICA方法用于脑电信号α波提取的研究[J]. 计算机工程与应用, 2008, 44(29): 217-219.
[12]	周成鹏,柴晓冬. 一种新的复波恢复方法——FastICA[J]. 计算机工程与应用, 2007, 43(27): 34-36.