计算机科学 ›› 2015, Vol. 42 ›› Issue (9): 83-85.doi: 10.11896/j.issn.1002-137X.2015.09.017

• 网络与通信 • 上一篇    下一篇

基于自适应倒谱距离的强噪声语音端点检测

赵新燕,王炼红,彭林哲   

  1. 湖南大学电气与信息工程学院 长沙410082,湖南大学电气与信息工程学院 长沙410082,湖南大学电气与信息工程学院 长沙410082
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金(61174140),湖南省自然科学基金(14JJ4026)资助

Adaptive Cepstral Distance-based Voice Endpoint Detection of Strong Noise

ZHAO Xin-yan, WANG Lian-hong and PENG Lin-zhe   

  • Online:2018-11-14 Published:2018-11-14

摘要: 在有噪声干扰的情况下,传统的语音端点检测方法的检测准确度明显下降。为了在强背景噪声环境下有效区分出语音信号和非语音信号,针对倒谱距离端点检测方法进行了研究,提出了一种基于自适应倒谱距离的强噪声语音端点检测方法。本方法引入倒谱距离乘数和门限增量系数,针对不同信噪比采用不同的倒谱距离乘数,并采用自适应判决门限的方法进行语音端点检测。MATLAB仿真实验结果显示,在不同背景噪声和不同信噪比下,本方法对于语音端点检测具有较高的检测正确率,其端点检测效果明显优于传统端点检测方法,适用于强背景噪声下的端点检测。

关键词: 倒谱距离,自适应判决门限,强噪声,端点检测

Abstract: In the case of noise interference,accuracy of speech endpoint detection using the traditional method dramati-cally declines.In order to effectively distinguish the speech signal and non-voice signal in strong background noise environment,this paper presented a strong noise speech endpoint detection method based on adaptive cepstral distance.The method introduces cepstral distance multiplier and the threshold increment coefficient.Different cepstral distance multipliers are used for different SNR and adaptive decision threshold method is used for voice activity detection.MATLAB simulation results show that,under different background noise and different SNR,the method for voice activity detection has high detection accuracy.Its detection is better than the traditional endpoint detection method,and is suitable for endpoint detection under strong background noise.

Key words: Cepstral distance,Adaptive decision threshold,Strong noise,Endpoint detection

[1] 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,2009,5(24):133-135,9 Li Jing,Liu Fu,Wang Ling,et al.Improved technology for speech endpoint detection[J].Computer Engineering and Applications,2009,5(24):133-135,9
[2] 吕钊.噪声环境下的语音识别算法研究[D].合肥:安徽大学,2011 Lv Zhao.Research on speech recognition algorithm in noisy environment[D].Hefei:Anhui University,2009
[3] 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,2013,3(1):175-178 Zhang Ting,He Ling,Huang Hua,et al.Speech endpoint detection based on critical band and energy entropy[J].Journal of Computer Applications,2013,3(1):175-178
[4] Li Jie,Zhou Ping,Jing Xin-xing,et al.Speech endpoint detection method based on TEO in noisy environment[J].Procedia Engineering,2012,29(1):2655-2660
[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 Zhu Heng-jun,Yu Hong-bo,Wang Fa-zhi.Speech Endpoints Detection Algorithm Based on Support Vector Machine and Wavelet Analysis[J].Computer Science,2012,9(6):244-246,5
[6] Wei Xiao-dong,Hu Guang-rui,Ren Xiao-lin.Endpoint detection of noisy speech by the use of cepstrum [J].Engineering Village,2014,34(2):185-188
[7] 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,2000,8(10):95-97 Hu Guang-rui,Wei Xiao-dong.Endpoint Detection of Noisy Speech Based on Cepstrum[J].Acta Electronica Sinica,2000,28(10):95-97
[8] 沈红丽,曾毓敏,王鹏.一种改进的基于倒谱特征的带噪语音端点检测方法[J].通信技术,2009,2(2):156-158 Shen Hong-li,Zeng Yu-min,Wang Peng.An Improved Speech Endpoint Detection Method based on Cepstrum Distance[J].Communications Technology,2009,2(2):156-158
[9] 王博,郭英,李宏伟,等.基于倒谱距离的语音端点检测改进算法[J].空军工程大学学报(自然科学版),2006,7(1):59-63 Wang Bo,Guo Ying,Li Hong-wei,et al.An Improved Voice Activity Detection Method Based on Cepstrum Distance[J].Journal of Air Force Engineering University (Natural Science Edition),2006,7(1):59-63
[10] 缪炜,侯丽敏.基于倒谱距离窗移最小失真分割的语种辨识[J].上海大学学报(自然科学版),2007,3(2):116-120 Miu Wei,Hou Li-min.Language Identification Based on Minimum Distortion of Cepstrum Distance Segmentation[J].Journal of Shanghai University(Natural Science Edition),2007,3(2):116-120
[11] 于迎霞,史家茂.一种改进的基于倒谱特征的带噪端点检测方法[J].计算机工程,2004,0(19):85-87Yu Ying-xia,Shi Jia-mao.A Modified Endpoint Detection Me-thod of Noisy Speech Based on Cepstral[J].Computer Enginee-ring,2004,0(19):85-87
[12] 蒋建中,张东方,张连海.一种新的强噪声环境下的语音增强算法[J].计算机工程与应用,2013,9(20):222-225 Jiang Jian-zhong,Zhang Dong-fang,Zhang Lian-hai.Speech enhancement algorithm for high noise environment[J].Computer Engineering and Applications,2013,9(20):222-225

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!