speech-signal-processing

自己提取的讯飞输入法语音识别组件，可绿色运行，解压双击iFlyVoice.exe即可运行，语音识别能力比较强！(The voice recognition component extracted by Xunfei can be operated in green, decompressed and double-clicked iFlyVoice.exe can be operated, and the voice recognition ability is relatively strong!)

本篇文章是要使针对HMM初学者，该文主要介绍了HMM原理(This article is to make for beginners HMM, the article mainly introduces the principle of HMM)

一个简易的端点检测程序，已经实现，包括基于过零率、短时能量的双门限判决方法。(a simple endpoint detection procedures has been achieved, including on the basis of zero rate Short-term dual energy threshold judgment method.)

利用DTW模版匹配算法实现0~9十个数字的识别。(use DTW template matching algorithm 0-9 10-digit identification.)

量子粒子群算法应用。对三个水听器的位置定位，在假设水听器位置已知情况下，以及其他方法估计得到的时延，通过量子粒子群算法计算，验证量子粒子群算法的计算精度。(Quantum particle swarm optimization application. Position location of the three hydrophones in the hydrophone position assumed known case, and other methods for estimating time delay obtained by calculating the quantum PSO QPSO verify the accuracy of the algorithm.)

采样小波包分解语音信号，分解为3层，并求出分解系数(Speech signal using wavelet packet decomposition，decomposing 6 level，and attain decomposition coefficient)

用三种经典的方法对语音信号进行增强，效果还不错并且三种方法的比较(With three classical methods of speech signal enhancement, the results were good and Comparison of Three Methods)

回声消除算法比较，仿射投影APA与NLMS算法比较(Echo cancellation apa nlms)

code for voice analysis final code for sapeech recognition

实现已知训练序列的矢量量化器（LBG）算法。初始码书从训练序列每隔五个样本选取一组(Achieve a known training sequence of the vector quantizer (LBG) algorithm. The initial codebook from the training sequence every five samples to select a group of)