首页 | 本学科首页   官方微博 | 高级检索  
     检索      

高噪声环境下的语音活动检测技术
引用本文:胡大雷,刘珩.高噪声环境下的语音活动检测技术[J].中国农业大学学报,2005,10(3):65-68.
作者姓名:胡大雷  刘珩
作者单位:中国农业大学,信息与电气工程学院,北京,100083
摘    要:以MOTOROLA公司生产的DSP56F801芯片为核心搭建系统硬件电路,对语音信号进行处理。采用能够根据背景噪声变化而自适应调节门限的算法对语音活动进行精确检测,实现整机系统在高噪声环境下的正常通讯。实际检测结果表明:在100、110、115dB的强背景噪声环境下,系统识别率分别为100%、96%和94%,丢字漏字率分别为2%、5%和10%;在100~110、110-115dB的背景噪声环境,系统稳定性分别为100%和98%。采用此种算法,增强了系统的抗干扰能力,在高噪声和噪声不太稳定的环境下,实现了对语音活动的精确检测。

关 键 词:语音活动检测  短时能量  过零率  短时自相关  自适应门限
文章编号:1007-4333(2005)03-0065-04
修稿时间:2004年11月25

Voice detection technology (VDT) in a background of high noise
Hu Dalei,Liu Heng.Voice detection technology (VDT) in a background of high noise[J].Journal of China Agricultural University,2005,10(3):65-68.
Authors:Hu Dalei  Liu Heng
Abstract:In order to identify the voice activity accurately in a background of 100-115dB high noise, voice signals were interpreted by using a circuit based on the DSPF801 chip produced by the Motorola. The voice detection algorithm used in the circuit could adjust threshold automatically according to the change of noise signals, which ensured a normal communication of the whole system. The test results showed that the detection rate reached 100%, 96% and 94% corresponding the noise levels of 100, 110 and 115dB respectively; and the words loss rate were 2%, 5% and 10% respectively. The system stability reached 100% and 98% respectively in high noise background of 100-110dB and 110-115dB. The system ability on anti-jamming was improved and a precision detection of VD was implemented in a high noise background or to unstable noise signals by the developed algorithm.
Keywords:VAD (voice activity detection)  short-time energy  zero-cross ratio  short-time auto-correlation  adaptive threshold
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《中国农业大学学报》浏览原始摘要信息
点击此处可从《中国农业大学学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号