与穆演讲语音quantization_compare CS5的信噪比

This code is used to calculated Pitch of the input signal.

2400bps MELP语音编解码源程序。-2400 MELP voice codec source.

intel的ipp性能库的示例代码，在多核平台下可以充分利用多核的性能实现语音编码-intel performance library of ipp sample code, in multi-core platform can take full advantage of multi-core performance to achieve speech coding

openphone下载-openphone Download

vb的语音 识别例子的-vb example of the Speech Recognition

语音识别技术是2000年至2010年间信息技术领域十大重要的科技发展技术之一 语音识别是一门交叉学科，语音识别正逐步成为信息技术中人机接口的关键技术，语音识别技术与语音合成技术结合使人们能够甩掉键盘，通过语音命令进行操作。语音技术的应用已经成为一个具有竞争性的新兴高技术产业。-voice recognition technology from 2000 to 2010 among the field of information technology in 10 major technologies voice recognition is one of an interdisciplinary, voice recognition is gradually becoming the information technology a key man-machine interface technology, voice recognition technology and voice synthesis technologies enable people to get rid keyboard, through voice commands to operate. The application of voice technology has become a competitive emerging high-tech industries.

语音增量调制编码。deltamodulation 语音增量调制编码。deltamodulation 语音增量调制编码。deltamodulation-Voice delta modulation encoding. Voice deltamodulation delta modulation encoding. Voice deltamodulation delta modulation encoding. deltamodulation

16kb/s Low Delay CELP 算法 -16kb/s Low Delay CELP algorithm

voip电话设计资料，语音信号详解、技术原理等-voip phone design data, voice signal Detailed technical rationale

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.