强噪声环境下改进的语音端点检测算法

doi:10.11772/j.issn.1001-9081.2014.05.1386

计算机应用 ›› 2014, Vol. 34 ›› Issue (5): 1386-1390.DOI: 10.11772/j.issn.1001-9081.2014.05.1386

强噪声环境下改进的语音端点检测算法

鲁远耀,周妮

北方工业大学信息工程学院，北京 100144

收稿日期:2013-10-21 修回日期:2013-12-26 出版日期:2014-05-01 发布日期:2014-05-30
通讯作者: 周妮
作者简介:鲁远耀(1977-)，男，湖北英山人，副教授，博士，主要研究方向：通信信号处理、图像处理、语音信号处理；周妮(1986-)，女，陕西西安人，硕士研究生，主要研究方向：语音信号处理；肖珂(1980-)，男，吉林松原人，副教授，博士，主要研究方向：无线MIMO通信；叶青(1977-)，女，河北保定人，副教授，硕士，主要研究方向：图像处理、模式识别。
基金资助:
“十一五”国家科技支撑计划重点项目

Improved speech endpoint detection algorithm in strong noise environment

LU Yuanyao,ZHOU Ni

College of Information Engineering, North China University of Technology, Beijing 100144, China

Received:2013-10-21 Revised:2013-12-26 Online:2014-05-01 Published:2014-05-30
Contact: ZHOU Ni

摘要/Abstract

摘要：

为了提高强噪声环境下语音端点检测的正确率，克服传统的短时能量和短时过零率双门限语音端点检测算法在低信噪比（SNR）条件下检测性能急剧下降这一缺陷，提出了一种改进的语音端点检测算法。该方法对强噪声环境下的语音信号，首先进行小波阈值去噪，提高信噪比，再采用双门限法进行端点检测。实验结果表明，该算法具有一定的鲁棒性，在强噪声环境下仍能准确地进行语音端点检测，从而该算法的有效性得到验证。

Abstract:

To improve the correctness of speech endpoint detection in strong noise environment, and overcome the disadvantage in traditional dual-threshold speech endpoint detection based on short-time energy and short-time zero-crossing rate, whose performance degrades sharply in low Signal-to-Noise Ratio (SNR) environment, an improved speech endpoint detection algorithm was proposed. In this method, the noisy speech signal was de-noised to enhance SNR at first, then the dual-threshold speech endpoint detection algorithm was used to detect the endpoints of the de-noised speech signal. The experimental results indicate that the proposed method not only has strong robustness, but also can achieve high detection accuracy in strong noise environment, so the effectiveness of the algorithm is proved.

中图分类号:

TN912.34

鲁远耀周妮. 强噪声环境下改进的语音端点检测算法[J]. 计算机应用, 2014, 34(5): 1386-1390.

LU Yuanyao ZHOU Ni. Improved speech endpoint detection algorithm in strong noise environment[J]. Journal of Computer Applications, 2014, 34(5): 1386-1390.

参考文献

［1］LIU H, LI X, ZHENG Y, et al. Speech endpoint detection based on improved adaptive band-partitioning spectral entropy ［J］. Journal of System Simulation, 2008,20(5):1366-1371.(刘华平,李昕,郑宇,等.一种改进的自适应子带谱熵语音端点检测方法［J］.系统仿真学报,2008,20(5):1366-1371.)
［2］WANG S, XU G, ZHANG A, et al. Research of VAD method based on multi voice characteristic parameter ［J］. Computer Engineering and Design, 2012,33(2):684-687.(汪石农,许钢,张爱雪,等.多语音特征参数的端点检测方法研究［J］.计算机工程与设计,2012,33(2):684-687.)
［3］ZHANG T, HE L, HUANG H, et al. Speech endpoint detection based on critical band and energy entropy ［J］. Journal of Computer Applications, 2013,33(1):175-178.(张婷,何凌,黄华,等.基于临界频带及能量熵的语音端点检测［J］.计算机应用,2013,33(1):175-178.)
［4］DONOHO D L, JOHNSTONE J M. Ideal spatial adaptation by wavelet shrinkage ［J］. Biometrika, 1994,81(3):425-455.
［5］DONOHO D L. De-noising by soft-thresholding ［J］. IEEE Transactions on Information Theory, 1995,41(3):613-627.
［6］ZHOU X. Adaptive wavelet thresholding denoising algorithm based on μ law fit ［J］. Computer Engineering and Applications, 2011,47(27):141-143.(周夕良. 基于μ律拟合的小波自适应阈值去噪算法［J］.计算机工程与应用,2011,47(27):141-143.)
［7］LI J, CHENG C, JIANG T, et al. Wavelet de-noising of partial discharge signals based on genetic adaptive threshold estimation ［J］. IEEE Transactions on Dielectrics and Electrical Insulation, 2012,19(20):543-549.
［8］LI R, BAO C, XIA B, et al. Speech enhancement using the combination of adaptive wavelet threshold and spectral subtraction based on wavelet packet decomposition ［C］// Proceedings of the 2012 IEEE 11th International Conference on Signal Processing. Piscataway: IEEE Press, 2012:481-484.
［9］JIANG G, WANG J. A modified endpoint detection method ［J］. Control and Automation, 2006,22(13):138-139.(江官星,王建英.一种改进的检测语音端点的方法［J］.微计算机信息,2006,22(13):138-139.)
［10］GU Y, ZHAO H, WU B. An improved method of the voice endpoint detection ［J］. Computer Simulation, 2010,27(5):340-343.(顾亚强,赵晖,吴波.一种语音信号端点检测的改进方法［J］.计算机仿真,2010,27(5):340-343.)
［11］YE Y, DAI W. Signal de-noising in wavelet based on new threshold function ［J］. Journal of Computer Applications, 2006,26(7):1617-1619.(叶裕雷,戴文战.一种基于新阈值函数的小波信号去噪方法［J］.计算机应用,2006,26(7):1617-1619. )
［12］YE C, HUANG Y. New improvement of wavelet threshold de-noising algorithm ［J］. Computer Engineering and Applications, 2011,47(12):141-145.(叶重元,黄永东.小波阈值去噪算法的新改进［J］.计算机工程与应用,2011,47(12):141-145.)
［13］WANG R, ZHANG Y. New threshold function in wavelet threshold de-noising ［J］. Computer Engineering and Applications, 2013,49(15):215-218.(王瑞,张友纯.新阈值函数下的小波阈值去噪［J］.计算机工程与应用,2013,49(15):215-218. )
［14］LI J, LIU F, WANG L, et al. Improved technology for speech endpoint detection ［J］. Computer Engineering and Applications, 2009,45(24):133-135.(李晋,刘甫,王玲,等.改进的语音端点检测技术［J］.计算机工程与应用,2009,45(24):133-135.)
［15］HOU L, ZENG Y, JIAO B. Speech endpoints detection based on improved HHT in strong noisy environment ［J］. Computer Engineering and Applications, 2012,48(28):139-142.(侯丽霞,曾以成,焦蓓.强噪声环境下基于改进HHT的语音端点检测［J］.计算机工程与应用,2012,48(28):139-142.)

[1]	常峥, 罗萍, 杨波, 张晓晓. 基于HHT-MFCC和短时能量的慢性阻塞性肺病患者呼吸声识别[J]. 计算机应用, 2021, 41(2): 598-603.
[2]	杨健, 李振鹏, 苏鹏. 语音分割与端点检测研究综述[J]. 计算机应用, 2020, 40(1): 1-7.
[3]	刘伟波, 曾庆宁, 卜玉婷, 郑展恒. 基于双微阵列与卷积神经网络的语音识别方法[J]. 计算机应用, 2019, 39(11): 3268-3273.
[4]	王康, 董元菲. 基于角度间隔嵌入特征的端到端声纹识别模型[J]. 计算机应用, 2019, 39(10): 2937-2941.
[5]	向立, 严迪群, 王让定, 李孝文. 针对多种处理痕迹的数字语音取证算法[J]. 计算机应用, 2019, 39(1): 126-130.
[6]	姚煜, RYAD Chellali. 基于双向长短时记忆联结时序分类和加权有限状态转换器的端到端中文语音识别系统[J]. 计算机应用, 2018, 38(9): 2495-2499.
[7]	黄亮, 潘平, 周超. 基于量子隧穿效应的说话人真伪鉴别方法[J]. 计算机应用, 2017, 37(9): 2617-2620.
[8]	秦楚雄, 张连海. 低资源语音识别中融合多流特征的卷积神经网络声学建模方法[J]. 计算机应用, 2016, 36(9): 2609-2615.
[9]	汪海彬, 余正涛, 毛存礼, 郭剑毅. SMFCC:一种新的语音信号特征提取方法[J]. 计算机应用, 2016, 36(6): 1735-1740.
[10]	王昱洁, 蒋薇薇. 基于模糊C均值聚类与单类支持向量机的音频隐写分析方法[J]. 计算机应用, 2016, 36(3): 647-652.
[11]	张俊, 关胜晓. 基于改进的最大后验概率矢量量化和最小二乘支持向量机集成算法[J]. 计算机应用, 2015, 35(7): 2101-2104.
[12]	晁浩, 宋成, 彭维平. 基于发音特征的声效相关鲁棒语音识别算法[J]. 计算机应用, 2015, 35(1): 257-261.
[13]	朱国腾孙伟. 基于模板匹配的快速语音关键词检出方法[J]. 计算机应用, 2013, 33(11): 3138-3140.
[14]	胡峰松张璇. 基于梅尔频率倒谱系数与翻转梅尔频率倒谱系数的说话人识别方法[J]. 计算机应用, 2012, 32(09): 2542-2544.
[15]	周阿转俞一彪. 采用特征空间随机映射的鲁棒性语音识别[J]. 计算机应用, 2012, 32(07): 2070-2073.

强噪声环境下改进的语音端点检测算法

Improved speech endpoint detection algorithm in strong noise environment

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