计算机科学 ›› 2017, Vol. 44 ›› Issue (5): 304-307.doi: 10.11896/j.issn.1002-137X.2017.05.056

• 图形图像与模式识别 • 上一篇    下一篇

基于子带能熵比的语音端点检测算法

张毅,王可佳,席兵,颜博   

  1. 重庆市信息无障碍与服务机器人工程技术研发中心 重庆400065,重庆市信息无障碍与服务机器人工程技术研发中心 重庆400065,重庆市信息无障碍与服务机器人工程技术研发中心 重庆400065,重庆市信息无障碍与服务机器人工程技术研发中心 重庆400065
  • 出版日期:2018-11-13 发布日期:2018-11-13
  • 基金资助:
    本文受重庆市教委科学技术研究项目基金(KJ130511),重庆市科学技术委员会项目(cstc2015jcyjBX0066)资助

Speech Endpoint Detection Algorithm Based on Sub-band Energy-entropy-ratio

ZHANG Yi, WANG Ke-jia, XI Bing and YAN Bo   

  • Online:2018-11-13 Published:2018-11-13

摘要: 准确地识别语音端点是语音识别过程中的一个重要步骤。在低信噪比环境下,为更好地增强语音和噪声的区分度,提高语音端点检测系统的准确率,在分析了常规子带谱熵端点检测算法的基础上结合子带能量,提出了一种基于子带能熵比的语音端点检测算法。该算法将子带能量和子带谱熵的比值作为端点检测的重要参数,以此设定阈值进行语音端点的检测。实验表明,该算法快速高效,具有较高的鲁棒性,在较低的信噪比环境下能准确地进行语音端点检测。

关键词: 端点检测,子带谱熵,子带能量,子带能熵比,信噪比,鲁棒性

Abstract: It is an important step of speech recognition process to identify accurately the speech endpoint.Under the environment with low SNR,in order to enhance the discrimination of noise better and improve the accuracy of speech endpoint detection system,this paper proposesd a new type of speech endpoint detection algorithm based on sub-band energy-entropy-ratio.The proposed algorithm takes the ratio of short-time sub-band energy and sub-band spectral entropy as an important parameter of endpoint detection,and sets the threshold to speech endpoint detection.Experiments show that the algorithm is fast and efficient,and it also has strong robustness and can detect the voice endpoint under lower SNR accurately.

Key words: Endpoint detection,Sub-band energy,Sub-band spectral entropy,Sub-band energy-entropy-ratio,SNR,Robustness

[1] CAO Y L,LA D S,JIA S,et al.A speech Endpoint Detection Algorithm Based on Wavelet Transforms[C]∥Control and Decision Conference(2014 CCDC).2014:3010-3012.
[2] MAJSTOROVIC N,ANDRIC M,MIKLUC D.Entropy-based-algorithm for speech recognition in noisy environment[C]∥Te-lecommunication forum.2011:667-670.
[3] LU Y U,ZHOU N,XIAO K,et al.Improved speech endpoint detection algorithm in strong noise environment[J].Journal of Computer Applications,2014,4(5):1386-1390.(in Chinese) 鲁远耀,周妮,肖珂,等.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.
[4] FU J,WANG S W,CAO X L.The Research on Speech Endpoint Detection Algorithm Based on Spectrogram Row Self-correlation[C]∥International Conference on Computer Science and Network Technology.IEEE,2012:212-216.
[5] KYRIAKIEDS A,PITRIS C,SPANIANS A.Isolated WordEndpoint Detection using Time-Frequency Variance Kernels[C]∥IEEE Trans.on Signal,Systems and Computers.2011:1041-1045.
[6] ZHAO X Y,WANG L L,PENG L Z.Adaptive Cepstral Dis-tance-based Voice Endpoint Detection of Strong Noise[J].Computer Science,2015,42(9):83-86.(in Chinese) 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,2015,42(9):83-86.
[7] SHEN J L,HUNG J W,LEE L S.Robust Entropy-based Endpoint Detection for Speech Recognition in Noisy Environments[C]∥Proceedings of International Conference on Spoken Language Processing.IEEE ,1998:232-235.
[8] WU B F,WANG K C.Robust Endpoint Detection AlgorithmBased on the Adaptive Band-Portioning Spectral Entropy in Adverse Environments[J].IEEE Transactions on Speech and Audio Processing,2005,3(5):762-775.
[9] WANG L,LI C R.An Improved Speech Endpoint DetectionMethod Based on Adaptive Band-paritition Spectral Entropy[J].Computer Simulation,2010,27(12):373-375.(in Chinese) 王琳,李成荣.一种基于自适应谱熵的端点检测改进方法[J].计算机仿真,2010,27(12):373-375.
[10] MORADI N,NASERSHARIF B,AKBARI A.Robust speechrecognition using compression of Mei sub-bandenergies and temporal filtering[C]∥International Symposium on Telecommunications.2010:760-764.
[11] ZHU C M,TIAN L F,LI X Y,et al.Recognition of Cough Using Features Improved by Sub-band Energy Transformation[C]∥International Conference on Biomedical Engineering and Informatics.2013:251-255.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!