SPEECH AND LANGUAGE PROCESSING

语音的消噪程序，传统普减法的改进，有效去除背景噪声-Speech de-noising process, the traditional S & P subtraction improvements, effectively remove background noise

VC下使用wavein/waveout的SDK进行录放音的Demo-use wavein VC/waveout SDK audio recorders for the Demo

本文系统的介绍了语音识别的技术及其实现方法-This article introduces the technic and implement method of speech recognise

语音合成软件，包括Freephone两个模块和Mbrora

关于hmm仿真的资料，内容实用有效。希望对大家有所帮助-hmm simulation of the information, as practical and effective. We hope to help

语音识别与合成入门5，word或压缩包中内有matlab源码-speech recognition and synthesis 5 entry, word or compressed packages within Matlab FOSS

一个改进后的VQ语音识别代码 自己编写和改进的 感觉效果还不错-An improved speech recognition VQ code I have written and improve the feeling of the effect of good

语音识别与合成入门2，word或压缩包中内有matlab源码-speech recognition and synthesis 2 entry, word or compressed packages within Matlab FOSS

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.

pitch detection algorithms.