LBG分类算法

用初始室心随机法和扰动因子分裂法两种方法，比较不同方法不同参数设置时的分类性能。

-LBG classification algorithm vector quantization: vector normalization within a certain range for a particular type, consists of two steps: first generate a codebook, which is the speech feature vector space by the first process- also known as clustering　 speech parameter sequence as a vector, the reference code for classified- also known as quantization. Clustering algorithm: it is relatively simple and commonly used K-means clustering algorithm. LBG is a clustering algorithm, which is generally assumed that the codebook size is fixed, and for a power of 2. Codebook is small, then expanding until it reaches the requirements. It is often an existing classification split into two subclasses, and initial value with the new code word to each subclass. LBG algorithm on random data and a certain regularity (and meet certain Gaussian distribution) data classification, and look at the performance of the LBG algorithm, the initial chamber heart random disturbance factor-secession law are two