一种矢量量化中的码本优化方法  

One Optimization Method of Codebook in Vector Quantization

作　　者：张雷[1] 孙诗瑛[1] 

机构地区：[1]上海交通大学电子工程系

出　　处：《江苏理工大学学报（自然科学版）》1998年第3期89-93,共5页Journal of Jiangsu University of Science and Technology(Natural Science)

摘　　要：在语音压缩编码中，矢量量化占有很大比重和计算量．码本的好坏与方法的选择有很大的关系．笔者介绍了一种方法，将神经网络和隐含马尔可夫过程应用于矢量量化，从而产生了更为优良的码本．In the compressive endoding of speech signals, the vector quantization is a more bigger portion and has a large amount of computation. The quality of codebook is related with the selection methods. A method of appling neural network and hidden Markov method for the vector quantization is introduced, several simulated results are also given, thus a better codebook can be obtained by this method.

关 键 词：神经网络 矢量量化 码本 优化 语音压缩编码 

分 类 号：TN912.3[电子电信—通信与信息系统] TP18[电子电信—信息与通信工程]