ADPCM压缩解压编码，实现部分为C语言编写，把它用C++封装为两个接口，编码和解码，方便使用。8K 16bit。...

拷贝文件的java源代码 -copy of java source code

matlab时域处理的相关程序，通过matlab调用实现-matlab deal with time-domain procedures, through the realization of matlab call

语音识别中对声音的处理，端点检测的简单方法，利用ME做端点估计。-based on Mean energy for startenddetect

使用MATLAB编写的nlms滤波器程序代码！-Prepared using the MATLAB program code nlms filter!

这个才是好东西，语音识别相比大家都知道，但是目前市场上出现的效果都不是太好，这个代码也是语文转换，效果还可以，但是说话不能口音太重-This one is just good thing, speech recognition compare with all know , but now, the effect that appears on market does not be too good , this code is also Chinese conversion, effect return can, but speak can not accent value too

提取语音信号的lpc参数并进行时间归整，需要将wav语音文件放在指定目录下‘e:yyzl’-voice signal from the lpc parameters and time consolidation, need to wav sound files on the specified directory "e : yyzl"

G.729 源代码解码 开发工具VC -G.729 codec source code development tools VC

LMS算法实现自适应滤波 clear close all clc N=10000 设置仿真长度 信号产生参数设定 a1=-0.195 a1=-1.5955 a2=0.95 R0=[1,a1,a2 a1,1+a2,0 a2,a1,1] p=[1,0,0] r=inv(R0)*p 计算理论自相关函数 R=[r(1),r(2) r(2),r(1)] 生成理论自相关矩阵 p1=[r(2),r(3)] 生成互相关 h=inv(R)*p1 计算维纳解 Jmin=r(1)-h *p1 计算维纳解时最小均方误差 u=1/sum(eigs(R- LMS算法实现自适应滤波 clear close all clc N=10000 设置仿真长度 信号产生参数设定 a1=-0.195 a1=-1.5955 a2=0.95 R0=[1,a1,a2 a1,1+a2,0 a2,a1,1] p=[1,0,0] r=inv(R0)*p 计算理论自相关函数 R=[r(1),r(2) r(2),r(1)] 生成理论自相关矩阵 p1=[r(2),r(3)] 生成互相关 h=inv(R)*p1 计算维纳解 Jmin=r(1)-h*p1 计算维纳解时最小均方误差 u=1/sum(eigs(R))

使用gabor变换作语音识别，下载自剑桥的实验室的网站，有兴趣的可以去网站上找资料-used for voice recognition, Cambridge downloaded from the website of the laboratory, interested parties can go to find information on the web site

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. Training voice features prior to extract.