A new improved energy-zero entropy speech endpoint detection with low signal-to-noise ratio

HUANG Zhen-kun; ZHANG Xiao-bing; ZHU Yu-qing

Chinese

您当前的位置：

首页 >

文章列表页 >

A new improved energy-zero entropy speech endpoint detection with low signal-to-noise ratio

更新时间：2026-09-04

- A new improved energy-zero entropy speech endpoint detection with low signal-to-noise ratio
- Vol. 37, Issue 6, Pages: 19-23(2020)
- 作者机构：
  
  安徽工业大学机构电气与信息工程学院,安徽,马鞍山,24300
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2020
- 稿件说明：
移动端阅览
黄镇坤, 章小兵, 朱俞清. 低信噪比环境下改进的新能零熵语音端点检测[J]. 微电子学与计算机, 2020, 37(6): 19-23, 29.

HUANG Zhen-kun, ZHANG Xiao-bing, ZHU Yu-qing. A new improved energy-zero entropy speech endpoint detection with low signal-to-noise ratio[J]. 2020, 37(6): 19-23.
黄镇坤, 章小兵, 朱俞清. 低信噪比环境下改进的新能零熵语音端点检测[J]. 微电子学与计算机, 2020, 37(6): 19-23, 29. DOI：

HUANG Zhen-kun, ZHANG Xiao-bing, ZHU Yu-qing. A new improved energy-zero entropy speech endpoint detection with low signal-to-noise ratio[J]. 2020, 37(6): 19-23. DOI：

摘要

语音端点检测是语音处理和识别至关重要的一环.针对传统端点检测方法在低信噪比情况下语音端点检测正确率低，抗噪能力差等问题，本文提出了一种改进的新能零熵特征参数语音端点检测方法.该方法法通过对语音三个端点检测特征参数短时过零率，短时能量和基本谱熵分析研究并提出新的语音参数，即为短时能零熵值，最后采用双门限算法来进行端点检测.仿真实验表明，与传统的能零比端点检测法相比，该方法在不同低信噪比情况下有较高的端点检测准确性.

Abstract

Speech endpoint detection is an important part of speech processing and recognition.Traditional endpoint detection methods have low accuracy in speech endpoint detection and poor anti-noise ability under the condition of low signal-to-noise ratio

In this paper

an improved zero-entropy feature parameter speech endpoint detection algorithm is proposed.This method studies the short-time zero-crossing rate

short-time energy and basic spectral entropy of three speech endpoint detection feature parameters

and proposes a new speech parameter

namely

the short-time energy zero-entropy value. Finally

a two-threshold algorithm is adopted to carry out endpoint detection.Simulation results show that compared with the traditional zero-energy ratio endpoint detection method

this method has higher endpoint detection accuracy under different low SNR conditions.

关键词

Keywords

references

宋知用.MATLAB在语音信号分析与合成中的应用[M].北京:北京航空航天大学出版社, 2017: 75-80. DOI: 75

WU B F, WANG K C. Robust endpoint detection algorithm based on the adaptive band-partitioningspectral entropyin adverse environments[J]. IEEE Transactions on Speech and Audio Processing, 2005, 13(5):762-775. DOI: 762

HUNG J W, SHEN J L, LEE L S. Improved robustness for speech recognition under noisy conditions using correlated parallel model combination[C]// IEEE International ConferenceonAcoustics.IEEE, 1998: 553-556

赵东雪.低信噪比下语音识别系统的研究[D].浙江: 浙江工业大学, 2014.

韩志艳, 王旭, 王健.基于短时能零积和鉴别信息的语音端点检测[J].东北大学学报(自然科学版), 2009, 30(12):1690-1693. DOI: 1690

尹岩岩, 殷业, 罗汉文.基于短时能零熵的端点检测方法[J].计算机仿真, 2012, 29(11):408-411. DOI: 408

王满洪, 张二华, 王明合.基于双门限算法的端点检测改进研究[J].计算机与数字工程, 2017, 45(11):2223-2228. DOI: 2223

陈莹莹, 毕春艳, 龙建忠.低信噪比下的语音端点检测算法研究[J].电视技术, 2018, 42(6):9-12. DOI: 9

董胡, 钱盛友.改进的能量谱熵端点检测算法[J].测控技术, 2016, 35(6): 26-29. DOI: 26

董胡.基于先验信噪比和能零熵的语音端点检测算法[J].计算机技术与发展, 2017, 27(7): 72-75. DOI: 72

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A high-efficiency charge pump for ultra-low voltage boost systems

A review of large model development: technological evolution from BERT to Deepseek

Monte carlo analysis of V-layout trench SiC neutron detector

Aerial small object detection algorithm based on improved RT-DETR

Research on assembly action recognition based on MSS-YOLO-MPHands fusion architecture

Related Author

No data

Related Institution

No data

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰