无结构码的快速最邻近模式搜索  

Fast Nearest Neighbor Pattern Search for Nonstructured Codes

作　　者：成德源[1] 

机构地区：[1]深圳大学电子工程系

出　　处：《深圳大学学报（理工版）》1990年第1期21-26,共6页Journal of Shenzhen University(Science and Engineering)

摘　　要：本文提出二进制超平面试验(BHT)方法,使最邻近模式搜索复杂性随比特率线性增长,远低于传统的随比特率及空问维数均指数增长的 EFS 方法的搜索复杂性.BHT 方法已成功地应用于实时语音波形矢量量化编码.The demanding exhaustive codebook search can be avoided by more efficient algorithm、the Binary Hyperplane Testing (BHT)algorithm,for fast codebook searching when least Euclidean distance is the appropriate distortion or dissimilarity measure.Let N denote the size of a codebook,and k denote the dimension of a vector.The searteh complexity of the BHT algorithm increases linearly with the bit rate r=(log_2N)/k. The search complexity of the BHT algorithm is sufficiently low that it has been used to implement a real-time speech waveform vector quantizer with sampling rate8 KHz, dimension k=4,and codebook size N=128 usingasingle programmable signal processor, the TMS 32010.

关 键 词：无结构码 最邻近搜索 矢量量化 数据压缩 编码 BHT 

分 类 号：TN919.31[电子电信—通信与信息系统]