Normalized_LMS

基于矢量量化的孤立词语音识别系统看，性能良好，Matlab 实现！(Based on vector quantization of isolated word speech recognition system to see, good performance, Matlab to achieve!)

speech specgram code

这里面的代码是2DPCA的。这篇文章发表在PAMI上,Two-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition.google搜索已经引用681次。这里的代码是原作者的。这个分类不太好，语音识别是最近的，这是模式识别里的经典算法。(matlab code of 2DPCA)

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.)

采用加权网络中节点强度和权重都是幂率分布的模型，计算两个矩阵之间的欧氏距离，实现了对10个数字音的识别。( Using weighted model nodes in the network strength and weight are power law distribution, Calculation of the Euclidean distance between the two matrices, To achieve the recognition of 10 digital sound.)

在evmdm642平台下的一个语音采集-回放任务，用48K/秒的采样率采集立体声音频输入，用给定的FIR 滤波参数处理数据后再播放出来。注：内附个人整理的详细操作文档。(evmdm642 platform in a speech to the gathering-intervals task with 48 K/s sampling rate Acquisition stereo audio input, used to the FIR filter parameters for data processing later. Note : with a detailed personal finishing operations documentation.)

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)

本次课程设计主要介绍了语音信号的录制、语音信号的采集与分析、语音信号的采样、语音信号的频谱分析、加噪后的频谱分析、滤波器的设计以及对于语音信号的回放等知识。通过 Cool Edit录制一段语音信号，运用MATLAB对其进行时域与频域分析，然后设计滤波器加入噪声进行滤波处理，比较滤波前后始于波形或频谱的变化，最后实现对于语音的回放设计。(Digital voice processing filter design)

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)

目前2.4kbps的混合激励线性预测 (MELP) 语音编码方法已经被确定为美国新的联邦语音编码标准.本文提出了一种改进的MELP语音编码方法,利用滤波器相似度和基于LPC系数分类的矢量量化技术,可以把MELP的码率降到1.7kbps以下,仍有较好的合成语音质量.(An Improved MELP Speech Coder)