计算机科学 ›› 2016, Vol. 43 ›› Issue (Z11): 233-236.doi: 10.11896/j.issn.1002-137X.2016.11A.053

• 模式识别与图像处理 • 上一篇    下一篇

一种基于改进谱熵的语音端点检测方法

李艳,成凌飞,张培玲   

  1. 河南理工大学电气工程与自动化学院 焦作454000,河南理工大学电气工程与自动化学院 焦作454000,河南理工大学电气工程与自动化学院 焦作454000
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金(51244003),河南省高等学校矿山信息化重点学科开放实验室开放基金(KZ2012-01)资助

Speech Endpoint Detection Based on Improved Spectral Entropy

LI Yan, CHENG Ling-fei and ZHANG Pei-ling   

  • Online:2018-12-01 Published:2018-12-01

摘要: 针对常规谱熵端点检测法在非平稳噪声环境下检测效果差的缺陷,提出了一种基于子带谱熵幅度积参数的语音端点检测方法。该方法利用非平稳信号处理技术将语音信号的时域分析和频域分析相结合,在常规谱熵的基础上计算出子带谱熵,再结合时域中的短时平均幅度进行端点检测。仿真结果表明,与常规谱熵端点检测算法和短时平均幅度算法相比,该方法在各种噪声环境下的检测效果都比较好,鲁棒性增强,其有效性得到验证。

关键词: 端点检测,谱熵,短时平均幅度,鲁棒性

Abstract: In view of the problem that conventional spectral entropy speech endpoint detection algorithm’s detection effect is poor under the non-stationary noise,a new feature parameter-sub-band amplitude spectrum entropy was proposed.The new parameter detection of speech endpoint uses non-stationary signal processing technology to combine the signal of time domain and frequency domain characteristics.Firstly,the conventional spectral entropy speech endpoint detection algorithm is improved and the multi-band spectral entropy is calculated,then the endpoint is detected with the combination of short time average magnitude.The simulation results show that this method has better robustness and precision than conventional spectral entropy algorithm and average magnitude algorithm,which proves the effectiveness of the proposed method.

Key words: Endpoint detection,Spectral entropy,Short-time average magnitude,Robustness

[1] Ouzounov A.Noisy speech endpoint detection using robust feature [M]∥Biometric Authentication.New York:Spring International Publishing,2014:105-117
[2] Ouzounov A.Telephone speech endpoint detection using mean-delta feature[J].Cybernetics and Information Technologies,2014,4(2):127-139
[3] Ghosh P K,Tsiartas A,Narayanan S.Robust voice activity detection using long-term signal variability[J].IEEE transactions on Audio,Speech,and Language Processing,2011,9(3):600-613
[4] 韦国刚,周萍,杨青.一种简单的噪声鲁棒性语音端点检测方法[J].测控技术,2015,34(2):31-34
[5] 朱恒军,于泓博,王发智.小波分析和支持向量机相融合的语音端点检测算法[J].计算机科学,2012,9(6):244-246,5
[6] 蔡莲红,黄德智,蔡锐.现代语音技术基础与应用[M].北京:清华大学出版社,2003:26-29
[7] 赵新燕,王炼红,彭林哲.基于自适应倒谱距离的强噪声语音端点检测[J].计算机科学,2015,2(9):83-85
[8] 胡光锐,韦晓东.基于倒谱特征的带噪语音端点检测[J].电子学报,2000,28(10):95-97
[9] Zhao H,Zhao L X,Zhao K,et al.Voice activity detection based on distance entropy in noisy environment[C]∥5th InternationalJoint Conference on INC,IM S,and IDC.Seoul,Korea:IEEE Computer Society,2009:1364-1367
[10] 朴春俊,马静霞,徐鹏.带噪语音端点检测方法研究[J].计算机应用,2006,26(11):2685-2686
[11] 张宇波,邢立钊.基于小波分析与PSO-ELM的语音端点检测算法研究[J].中北大学学报(自然科学版),2016,7(1):33-37
[12] 赵欢,王纲金,赵丽霞.一种新的对数能量谱熵语音端点检测方法[J].湖南大学学报(自然科学版),2010,7(7):72-77
[13] 柳春.一种改进的基于短时平均幅度的语音端点检测算法研究[J].西北民族大学学报(自然科学版),2009,0(73):56-59
[14] Shen J L,Hung J W,Lee L S.Robust Entropy-based Endpoint Detection for Speech Recognition in Noisy Environments [C]∥ICSLP(S0160-5840).Sydney,Australia,1998:232-235
[15] Wu Bing-fei,Wang K C.Robust Endpoint Detection Algorithm Based on the Adaptive Band-Partitioning Spectral Entropy in Adverse Environments[J].IEEE Transactions on Speech and Audio Processing (S1063-6676),2005,13(5):762-775

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!