yuchuli

LMS多麦克风语音降噪的主程序是lmsspdn.m(Multi-microphone noise reduction LMS voice is the main program lmsspdn.m)

对一维语音信号，用正交匹配追踪的方法进行重构，首先对其进行了分帧，然后再一帧一帧的重构，最后计算了平均帧重构误差(One-dimensional speech signal reconstruction, orthogonal matching pursuit, the first of its sub-frame, and then again a reconstruction of a final calculation of the average frame reconstruction error)

压缩包中包括3个用于对语音增强中，增强语音质量测试的程序：分段信噪比提高测量、对数谱距离测量、信噪比测量。具体说明，请看文件文件说明。(Compression package, including three for speech enhancement, the enhanced voice quality testing procedures: Sub-noise ratio improve measurement of the distance spectrum measurement, signal to noise ratio measurement. Specify, see the paper documentation.)

语音识别中信号特征的提取，基因周期估计，共振峰估计等。(Signal feature extraction in speech recognition, cycle genes estimation, formant estimation,etc)

基于非线性主分量分析(PAST)的 自适应盲信号分离 (Based on nonlinear principal component analysis (PAST) Adaptive Blind Signal Separation)

VAD去噪算法，可以有效的过滤静音和无效的语音，同时消除了一些背景噪声。(VAD denoising algorithm, can effectively filter invalid mute and voice, while eliminating some background noise.)

语音增强电子书，国外经典教材，自适应滤波，卡尔曼滤波，最小均方算法等等(speech enhancement ebook)

WM8731语音芯片的驱动程序，完成录音和播放功能。主控制芯片为STM32RCT6。测试通过。(WM8731 voice chip driver to complete the recording and playback functions. The main control chip is STM32RCT6. Test pass.)

语音库开发工具源码，例程程序创建机读SAPI.SpVoice对象开发语音库。(Speech development tools source , routine program to create machine-readable SAPI.SpVoice speech object development .)

3、语音特征提取与分类 首先, 待识别语音转化为电信号后输入识别系统, 经过预处理后用数学方法提取语音特征信号, 提取出的语音特征信号可以看成该段语音的模式。(3, the voice feature extraction and classification First, to be recognized voice into electrical signals input recognition system, after pretreatment with a mathematical method to extract speech characteristic signal extracted speech characteristic signal can be seen as the voice segment model.)