文字阅读器，运行前须安装speechsdk51.exe和speechsdk51LangPack.exe语音引擎，在微软网站上可以下载到。-text reader, prior to the operation and installation speechsdk51.exe speechsdk51LangPack.exe voice engine, the Microsoft Web site to download.

语音增强算法，基于LsA-MMSE方法，并对其先验信噪比估计器进行了修改，具体过程参看Isal的论文。语音间隙间的音乐噪声也消除了。-speech enhancement algorithms, based on LsA - MMSE, and signal-to-noise ratio of its prior estimate for the changes, See specific process Isal theses. Voice gap between the music also

用三层小波神经网络实现的与文本无关说话人识别。（识别部分）。输入的是语音特征，输出的是识别结果。训练用的语音特征要事先提取出。-with three wavelet neural network has nothing to do with the text of Speaker Recognition. (Recognition). The admission of voice features, the output is the result of recognition. Trainin

enfrmae函数,可以用于对语音信号进行处理前的分帧-enfrmae function can be used to process the speech signal prior to framing