摘要
提出了基于互相关函数的检测元音的端点检测算法。在语音识别系统中产生错误识别的原因之一是端点检测有误差,在高信噪比情况下,准确地确定语音的端点并不困难,然而在低信噪比情况下,一些常规的端点检测方法,例如基于能量的端点检测方法就不能有效地工作。本文利用互相关函数检测元音的端点,然后根据元音和辅音的能量比一般相对稳定的特点确定出实际语音端点。实验结果表明,本方法可以在不同信噪比下提高端点检测的准确率。
An algorithm for endpoint detection which based on cross matic speech recognition （ASR） systems is the inaccurate detection correlation function is presented. A major cause of error in autoof the beginning and ending boundaries of test and reference patterns. Accurate determination of endpeints of speech is not very difficult if the SNR is high. Unfortunately, the conventional speech detection methods such as energy cannot work well in noisy environments. In the paper, cross correlation function is used to detect the endpoint of the vowels. The energy ratio of vowels and consonants is relatively steady and accordingly the endpoint of actual speech can be detected. The experimental results show the performance of endpoint detection can be improved by this method in various SNR environments.
出处
《微计算机信息》
北大核心
2007年第18期202-203,共2页
Control & Automation
基金
甘肃省自然科学基金(3ZS042-B25-001)
关键词
语音识别
端点检测
互相关函数
Speech recognigion, Endpoint detection, Cross correlation function
