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

G.711使用64Kbps的带宽，可将14bits转换成8bits。目前G.711有两个编码方式，A-law以及Mu-law。-G.711 defines two main compression algorithms, the µ -law algorithm (used in North America & Japan) and A-law algorithm (used in Europe and the rest of the world). Both are logarith

SERIES P: TELEPHONE TRANSMISSION QUALITY, TELEPHONE INSTALLATIONS, LOCAL LINE NETWORKS - Methods for objective and subjective assessment of quality

C SourceCode for SERIES P: TELEPHONE TRANSMISSION QUALITY, TELEPHONE INSTALLATIONS, LOCAL LINE NETWORKS - Methods for objective and subjective assessment of quality