改进的变步长最小均方误差电子耳蜗语音增强算法

doi:10.11772/j.issn.1001-9081.2017.04.1212

计算机应用 ›› 2017, Vol. 37 ›› Issue (4): 1212-1216.DOI: 10.11772/j.issn.1001-9081.2017.04.1212

• 应用前沿、交叉与综合 • 上一篇

改进的变步长最小均方误差电子耳蜗语音增强算法

徐文超, 王光艳, 陈雷

天津商业大学信息工程学院, 天津 300134

收稿日期:2016-09-14 修回日期:2016-12-27 出版日期:2017-04-10 发布日期:2017-04-19
通讯作者: 徐文超
作者简介:徐文超(1981-),男,河北衡水人,实验师,硕士,主要研究方向:模式识别、智能控制;王光艳(1975-),女,河北邯郸人,副教授,博士,主要研究方向:语音信号处理;陈雷(1980-),男,河北唐山人,副教授,博士,主要研究方向:盲信号处理,智能计算。
基金资助:
国家自然科学基金资助项目（61401307）；天津市应用基础与前沿技术研究计划项目（14JCZDJC32600）；天津商业大学青年科研基金资助项目（150111）；国家级大学生创新创业训练计划项目（201610069085）。

Speech enhancement algorithm based on improved variable-step LMS algorithm in cochlear implant

XU Wenchao, WANG Guangyan, CHEN Lei

College of Information Engineering, Tianjin University of Commerce, Tianjin 300134, China

Received:2016-09-14 Revised:2016-12-27 Online:2017-04-10 Published:2017-04-19
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61401307), the Tianjin Research Program of Application Foundation and Advanced Technology (14JCZDJC32600), the Youth Research Foundation of Tianjin University of Commerce (150111), the National College Students' Innovation and Entrepreneurship Training Program (201610069085).

摘要/Abstract

摘要： 针对外部强噪声环境下电子耳蜗语音质量受损、适应性差等问题，提出了基于谱减法和变步长最小均方误差（LMS）自适应滤波算法联合去噪的改进方法，并以该方法构建了一个电子耳蜗前端语音预处理系统。利用变步长LMS自适应滤波算法输出误差的平方项来调节步长，采用步长值固定与变化相结合的方法，解决了自适应滤波算法收敛速度慢、稳态误差大的问题，适应性得到提高，提高了语音信号通信质量。该系统以TMS320VC5416和音频编解码芯片TLV320AIC23B为核心，通过多通道缓冲串口（McBSP）和串行外设接口（SPI）实现了语音数据的高速采集和实时处理。实验仿真和测试结果表明该算法消除噪声性能好，信噪比在低输入信噪比情况下提高约10 dB，语音质量感知评价（PESQ）分值也得到较大提高，能有效提高语音信号质量，且该系统性能稳定，能进一步提高耳蜗前端语音的清晰度和可懂度。

关键词: 电子耳蜗, 噪声抑制, 最小均方误差, 自适应滤波, 语音增强

Abstract: In order to improve the quality of speech signal and adaptability of cochlear implant under strong noise background, an improved method was proposed based on the combination of spectral subtraction and variable-step Least Mean Square error (LMS) adaptive filtering algorithm, and a speech enhancement hardware system for cochlear implant was constructed with this method. Concerning the problem of slow convergence rate and big steady-state error, the squared term of output error was used to adjust the step size of variable-step LMS adaptive filtering algorithm; besides, the combination of fixed and changed values of step was also considered, thus improved the adaptability and quality of speech signal. The speech enhancement hardware system for cochlear implant was composed of TMS320VC5416 and audio codec chip TLV320AIC23B, high-speed acquisition and real-time processing of voice data between TMS320VC5416 and TLV320AIC23B were realized by the interface of Muti-channel Buffered Serial Port (McBSP) and Serial Peripheral Interface (SPI).The Matlab simulation and test results prove that the proposed method has good performance in eliminating noise, the Signal-to-Noise Ratio (SNR) can be increased by about 10 dB in the case of low input SNR, and Perceptual Evaluation of Speech Quality (PESQ) score can be also greatly enhanced, the quality of the voice signal is improved effectively, and the system based on the proposed algorithm has stable performance which further improves the clarity and intelligibility of voice in cochlear implant.

Key words: cochlear implant, noise suppression, Least Mean Square error (LMS), adaptive filtering, speech enhancement

中图分类号:

TP391.4

徐文超, 王光艳, 陈雷. 改进的变步长最小均方误差电子耳蜗语音增强算法[J]. 计算机应用, 2017, 37(4): 1212-1216.

XU Wenchao, WANG Guangyan, CHEN Lei. Speech enhancement algorithm based on improved variable-step LMS algorithm in cochlear implant[J]. Journal of Computer Applications, 2017, 37(4): 1212-1216.

参考文献

[1] 胡航.现代语音信号处理[M]. 北京:电子工业出版社, 2014:15-20.(HU H. Modern Speech Signal Processing[M]. Beijing: Publishing House of Electronics Industry, 2014:15-20.)
[2] 覃景繁, 欧阳景正.一种新的变步长LMS自适应滤波算法[J]. 数据采集与处理, 1997, 12(3): 171-172.(QIN J F, OUYANG J Z. A novel variable step size LMS adaptive filtering algorithm based on sigmoid function[J]. Journal of Data Acquisition & Processing, 1997, 12(3): 171-172.)
[3] 倪锦根, 李峰.一种新的变步长最小均方自适应滤波算法[J]. 信息与电子工程, 2008, 6(1):10-13.(NI J G, LI F. A novel variable step-size LMS adaptive filtering algorithm[J]. Information and Electronic Engineering, 2008, 6(1):10-13.)
[4] 朱斌, 马艳.一种新的变步长LMS算法分析[J].计算机仿真, 2008, 25(9):93-95.(ZHU B, MA Y. Performance analysis of a novel variable step size LMS algorithm[J]. Computer Simulation, 2008, 25(9):93-95.)
[5] 任志钊, 徐建成, 闫永鹏. 一种改进的变步长LMS自适应滤波算法及性能分析[J]. 计算机应用研究, 2011, 28(3):954-956.(REN Z Z, XU J C, YAN Y P. Improved variable step size LMS adaptive filtering algorithm and its performance analysis[J]. Application Research of Computers, 2011, 28(3): 954-956.)
[6] 高榕, 张仕凯, 李靖, 等.自适应滤波器消除语音信号中混合噪声[J]. 河南科技大学学报(自然科学版), 2012, 33(4):42-45.(GAO R, ZHANG S K, LI J, et al. Adaptive filter to eliminate mixed noise in speech signal[J]. Journal of Henan University of Science & Technology (Natural Science), 2012, 33(4):42-45.)
[7] 彭军, 王忠.基于多窗谱相关加权语音增强[J].计算机仿真, 2011, 28(3):142-145.(PENG J, WANG Z. Correlation weighting enhancement of speech based on multitaper spectrum[J]. Computer Simulation, 2011, 28(3):142-145.)
[8] 高鹰, 谢胜利.一种变步长LMS自适应滤波算法及分析[J].电子学报, 2001, 29(8): 1094-1097.(GAO Y, XIE S L. A variable step size LMS adaptive filtering algorithm and its analysis[J]. Acta Electronica Sinica, 2001, 29(8): 1094-1097.)
[9] 华强, 夏哲雷, 祝剑英.一种改进的变步长LMS自适应滤波算法及仿真[J]. 中国计量学院学报, 2012, 23(3):304-308.(HUA Q, XIA Z L, ZHU J Y. A modified variable step size LMS adaptive filtering algorithm and its simulation[J]. Journal of China University of Metrology, 2012, 23(3):304-308.)
[10] 代少升, 马东鸽. 基于DSP的语音信号自适应滤波系统的设计与实现[J]. 重庆邮电大学学报(自然科学版), 2011, 23(4):432-435.(DAI S S, MA D G. Design and realization of the voice signal self_adaptive filtering system based on DSP[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2011, 23(4):432-435.)
[11] DAWSON P W, MAUGER S J, HERSBACH A A. Clinical evaluation of signal-to-noise ratio based noise reduction in nucleus cochlear implant recipients[J]. Ear and Hearing, 2011, 32(3): 382-390.
[12] DERAKHSHAN N, AKBARI A, AYATOLLAHI A. Noise power spectrum estimation using constrained variance spectral smoothing and minima tracking[J]. Speech Communication, 2009, 51(11):1098-1113.
[13] MACHEREY O, DEEKS J M, CARLYON R P. Extending the limits of place and temporal pitch perception in cochlear implant users[J]. Journal of the Association for Research in Otolaryngology, 2011, 12(2): 233-251.
[14] SUN Y B, HU Y L. Communication mechanism based on test platform for cochlear chip[J]. Computer Measurement & Control, 2013, 21(12):3309-3313.
[15] 王瑜琳, 田学隆, 高雪利.自适应滤波语音增强算法改进及其DSP实现[J].计算机工程与应用, 2015, 51(1):208-212.(WANG Y L, TIAN X L, GAO X L. DSP realization of modified speech enhancement algorithm based on adaptive filters[J]. Computer Engineering and Applications, 2015, 51(1):208-212.)
[16] 陈勇, 田金鹏, 刘燕平. 一种新的变步长LMS自适应滤波算法[J]. 电子测量技术, 2015, 38(4):27-31.(CHEN Y, TIAN J P, LIU Y P. New variable step size LMS adaptive filtering algorithm[J]. Electronic Measurement Technology, 2015, 38(4):27-31.)
[17] 陈兆岭, 刘国海, 杨晨星. 提高谐波电流检测性能的LMS/LMF自适应滤波器[J]. 仪器仪表学报, 2014, 34(5):1036-1042.(CHEN Z L, LIU G H, YANG C X. LMS/LMF adaptive filter for harmonic current detection performance improvement[J]. Chinese Journal of Scientific Instrument, 2014, 34(5):1036-1042.)

改进的变步长最小均方误差电子耳蜗语音增强算法

Speech enhancement algorithm based on improved variable-step LMS algorithm in cochlear implant

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	欧跃发, 杨鸣坤, 慕德俊, 柯捷, 马文涛. 基于广义最大Versoria准则的稀疏自适应滤波算法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3325-3331.
[2]	冯子凯, 陈立家, 刘名果, 袁蒙恩. 基于结构自适应滤波方法的非线性系统辨识[J]. 计算机应用, 2020, 40(8): 2319-2326.
[3]	龙超, 曾庆宁, 罗瀛. 基于噪声抵消与波束形成的小阵语音增强[J]. 计算机应用, 2020, 40(8): 2386-2391.
[4]	张皓然, 王学渊, 李小霞. 基于自适应阈值活动语音检测和最小均方误差对数谱幅度估计的低信噪比降噪算法[J]. 计算机应用, 2020, 40(6): 1763-1768.
[5]	吴庆贺, 吴海锋, 沈勇, 曾玉. 工业噪声环境下多麦状态空间模型语音增强算法[J]. 计算机应用, 2020, 40(5): 1476-1482.
[6]	宋芸, 张元科, 卢虹冰, 邢宇翔, 马建华. 基于区域内容感知核范数的低剂量CT影像去噪[J]. 计算机应用, 2020, 40(4): 1177-1183.
[7]	王永彪, 张文喜, 王亚慧, 孔新新, 吕彤. 拉普拉斯分布下的MMSE谱减语音增强算法[J]. 计算机应用, 2020, 40(3): 878-882.
[8]	李艳生, 刘园, 张毅. 基于感知掩蔽的重构非负矩阵分解单通道语音增强算法[J]. 计算机应用, 2019, 39(3): 894-898.
[9]	葛宛营, 张天骐. 基于掩蔽估计与优化的单通道语音增强算法[J]. 计算机应用, 2019, 39(10): 3065-3070.
[10]	李慧敏, 张治中, 李琳潇. LTE-A系统中基于小区参考信号的信道估计算法[J]. 计算机应用, 2018, 38(7): 2009-2014.
[11]	蒋茂松, 王冬霞, 牛芳琳, 曹玉东. 稀疏正则非负矩阵分解的语音增强算法[J]. 计算机应用, 2018, 38(4): 1176-1180.
[12]	张新明, 康强, 程金凤, 涂强. 采用自适应四点窗中点滤波的高椒盐噪声滤除方法[J]. 计算机应用, 2017, 37(3): 832-838.
[13]	张新明, 程金凤, 康强, 王霞. 迭代自适应权重均值滤波的图像去噪[J]. 计算机应用, 2017, 37(11): 3168-3175.
[14]	魏丹丹, 周翊, 师黎明, 刘宏清. 基于反双曲正弦函数的抗冲激块稀疏自适应滤波算法[J]. 计算机应用, 2017, 37(1): 197-199.
[15]	刘金刚, 周翊, 马永保, 刘宏清. 用于自动语音识别系统的切换语音功率谱估计算法[J]. 计算机应用, 2016, 36(12): 3369-3373.