改进的LBG算法及浊音隶属度码本的训练  

Improved LBG Algorithm and Training of Voiced Membership Codebook

作　　者：田春环 姜占才[1] 

机构地区：[1]青海师范大学物理系,西宁810008

出　　处：《电脑开发与应用》2015年第3期61-63,66,共4页Computer Development & Applications

摘　　要：为了改善MELP声码器解码端混合激励信号的性能,提出了五维浊音隶属度矢量的概念及其提取算法,用其提取并建立了浊音隶属度码本的训练样本集;用改进的LBG算法训练了浊音隶属度码本;将此码本运用到混合激励声码器中。仿真实验表明,解码语音的质量较之LPC声码器有显著的提高。In order to improve the performance of MELP vocoder decoding end mixed excitation signal, the concept of a five dimensional voiced membership degree vector and its extraction algorithm is put forward, for the extraction and the establishment of the voiced membership codebook training set;with improved LBG algorithm training voiced membership codebook;this codebook to use mixed excitation vocoder. Simulation results show that,the quality of the decoded speech is significantly improved than that of LPC vocoder.

关 键 词：声码器 矢量量化 LBG算法 浊音隶属度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]