speech recognition with DTW

mfcc.m 用于语音识别上的mfcc特征参数提取函数。(mfcc.m mfcc characteristic parameters for speech recognition on the extraction function.)

采用MFCC方法提取训练集样本或测试集样本语音特征参数的MATLAB程序，仿真时需先将voicebox语音处理工具箱添加到MATLAB软件中(The MFCC method is used to extract the MATLAB program of the training set sample or the test set sample speech feature parameters. The voicebox voice processing toolbox is added to the MATLAB software first.)

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.)

采用广义旁瓣抵消（GSC）自适应波束形成方法实现时域和频域滤波，采用LMS自适应算法，最终实现语音增强。（文件中包含纯净语音及不同信噪比的带噪语音）(Generalized sidelobe canceller (GSC) adaptive beamforming method to achieve time-domain filtering using the LMS adaptive algorithm, and ultimately the speech enhancement)

计算声音信号的总声压级，1/3/倍频程声压级，总响度，特性响度，尖锐度(Calculation of the total sound pressure level of the voice signal, 1/3/octave sound pressure level, the total loudness, loudness characteristics, acute severe)

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.)

本文介绍MVDR算法实现及其改进 用于多麦克风语音增强(The minimum variance distortionless response (MVDR), originally developed by Capon for frequency-wavenumber analysis, is a very well established method in array process-ing. It is also used in spectral estimation. The aim of this paper is to show how the MVDR method can be used to es-timate the magnitude squared coherence (MSC) function, which is very useful in so many applications but so few methods exist to estimate it)

单点定位的滤波程序，可以获得速度信息和位置信息,这是一个滤波程序，对语音信号滤波。(A single point positioning of the filtering process, get the speed of information and location information,this is a wiener filtering process to filter the speech signal.)

c#写的语音识别程序，识别效率还算可以。且根据识别可以给出相应的识别百分比。适合研究语音识别以及tts的参考！(c# to write the speech recognition process, identify efficiency figure. And recognition can be given according to the percentage of the corresponding identification. Tts speech recognition, as well as for research reference!)

一个盲信号分离的卷积方法，适合分离实际卷积混合的模型，希望对初学者有帮助。(Convolution of a blind signal separation method, suitable for separation of the real convolution mixture model, want to help beginners.)