基于单边自相关线性预测噪声中汉语语音识别

Noisy Chinese Speech Recognition Based on Linear Prediction of One-sided Autocorrelation Sequence

对含噪语音在自相关域上进行处理 ,以其自相关函数值为参数进行端点检测 ,以基于单边自相关序列的LPC倒谱系数作为语音的特征参数进行语音识别 ,实验表明 :这种方法较好地消除了噪声对语音信号的干扰 ,并获得了较高的识别率。在信号的信噪比低而自相关性又强时 ,此法能体现出不同一般的优势 ,为实际应用提供了可能。

A new way is supplied to increase the recognition rate of Chinese speech in nois e.It includes two parts. One is using the autocorrelation function to detect the speech terminal, the other is using the coefficients based on the one\|sided au t ocorrelation sequence to replace the original speech signal and then extract the speech feature to recognize.Isolated word recognition experiment based on DTW s hows:it can reduce the disturbance of noise effectively and get the high recogni tion rate.It is of great advantage to apply when SNR (signal to noise rate) is l ow.