中文说明：
语音识别是近年来发展非常迅速的一项计算机智能技术，广泛应用在语音控制、身份识别等多个领域。本次项目主要研究语音识别的预处理过程和特征参数的提取环节。通过对原始语音信号进行预加重和分帧、加窗，滤除低频干扰，提升对语音识别有用的部分，消除了部分噪音和失真。预处理之后进行信号的特征提取，主要选取了短时平均过零率和MFCC两个特征参数，应用matlab软件绘制波形图并提取特征参数矩阵，为之后的语音信号的识别打下了基础。
English Description：
Speech recognition is a computer intelligent technology which has developed rapidly in recent years. It is widely used in speech control, identity recognition and other fields. This project mainly studies the preprocessing process of speech recognition and the extraction of feature parameters. Through pre emphasis, frame division and windowing of the original speech signal, the low-frequency interference is filtered, the useful part of speech recognition is improved, and some noise and distortion are eliminated. After preprocessing, the signal feature extraction is carried out. The short-term average zero crossing rate and MFCC are selected as the main feature parameters. The waveform is drawn by MATLAB software and the feature parameter matrix is extracted, which lays the foundation for the subsequent speech signal recognition.