Sound separation by ICA

这是Matlab的一个语音工具箱 很有用-This is a Matlab toolbox very useful voice

国际上最新的说话人识别算法的源程序，内置语音训练数据-The latest international speaker recognition algorithm source code, built-in voice training data

声音信号的短时能量matlab实现程序源码-Audio signal to achieve short-term energy program source code matlab

本程序可以产生一组正态模拟数，用来模拟实际生产中服从或近似服从正态分布的数据，很有用。-This procedure can generate a group of normal simulation the number used to simulate the actual production or similar to obey normal distribution of data, very useful.

Hammerstein系统识别，其状态空间子系统包括形成的Hammerstein系统的线性部分。

这是一个在语音识别中求Mel倒谱系数的matlab程序。 这个程序里面还需要用到几个其他的函数，都在VoiceBox工具箱里面，可以到网上下载-Calculate the mel cepstrum of a signal，The program also needs to be used in several other functions, in VoiceBox toolbox, can to download

大规模连续语音识别工具，比较实用。可以做实际建模-large-scale continuous speech recognition tools, more practical. Modeling can do practical

静态Huffman的小程序，帮助理解Huffman的原理，不可多得。-small procedure to help understand the principle Huffman indeed.

该程序是非特定人语音识别程序，原来在SPCE500A下运行，能识别并应答16个命令，存储空间为128K字节。-the procedures were non-specific voice recognition procedure, in SPCE500A original run, Recognition and Response to 16 orders, storage space for 128K bytes.

基于GMM的概率神经网络PNN具有良好的泛化能力，快速的学习能力，易于在线更新,并具有统计学的贝叶斯估计理论基础，已成为一种解决像说话人识别、文字识别、医疗图像识别、卫星云图识别等许多实际困难分类问题的很有效的工具。而且PNN不但具有GMM的大部分优点，还具有许多GMM没有的优点，如强鲁棒性，需要更少的训练语料，可以和其他网络其他理论无缝整合等。-GMM based probabilistic neural network PNN good generalization ability, the ability to learn fast, easy online updates, and with the Bayesian statistical theory based on estimates, and has become a solution as speaker recognition, text recognition, medical image recognition, satellite images and other real recognition when difficulties classification of very effective tool. But GMM PNN is not only the most advantages, but also has many advantages GMM not as strong robustness, require less training corpus, and other networks to other theories, such as seamless integration.