nlmsbeamformer2

语音识别功能，可以直接说话进行识别，然后转换成文字(Speech recognition)

function [Coefficients,residual,pitch,Gain,parcorCoefficients,stream,B,crossmat,error_stream] = lpcanalysis(speechtodecode,samplerate,L,windowtime,preemp)

用于汉语语调识别的程序，可以识别我们说话中的四个声调。已通过测试(Chinese tone recognition for the program, has been tested)

基于LMS算法的变换域的源程序，里面给出了学习曲线，迭代后的输出曲线(LMS algorithm based on the Domain source, which is a learning curve, the output iterative curve)

这是一个语音的文件的一个FFT转换文件,是用C++写的源程序,相信对大家有用(This is a voice of a paper document conversion FFT is written in C source files, it may be useful to think)

计算语音、音频信号的信噪比程序（包含音频样本文件）(Calculation of voice, audio program signal to noise ratio (including the audio sample file))

基于GMM的MFCC算法的说话人识别，Maltab的高斯混合模型，12维。(MFCC speaker recognition algorithm based on GMM)

C语音实现Matlab corrcoef（求两个信号的互相关系数），包括了Matlab的对比验证源代码(Calculate the correlation coefficient refer the Matlab function:corrcoef)

分段信噪比测试，主要是用于语音增强，语音编码后的测试使用(segment SNR test, primarily for speech enhancement, speech coding after testing)

使用TD-PSOLA（td-psola、psola）算法，做了一个语音合成，实现语音声调的变调，时长的变化等功能。参考praat源码，提取出其合成方法，效果不错。需要提供pitchtier、durationtier、pointprocess等准换信息文本（可由praat产生）供readfile函数读入(Use TD-PSOLA (TD-PSOLA, PSOLA algorithm, made a speech synthesis, speech tone tone sandhi, long-term changes in the function. Reference Praat source code, extract its synthetic method, the effect of the same.)