首页|改进的LBG算法及浊音隶属度码本的训练

改进的LBG算法及浊音隶属度码本的训练

扫码查看
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。
Improved LBG Algorithm and Training of Voiced Membership Codebook
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.

vecodervector quantization(VQ)LBG algorithmvoiced membership

田春环、姜占才

展开 >

青海师范大学物理系,西宁 810008

声码器 矢量量化 LBG算法 浊音隶属度

2015

电脑开发与应用
中国北方自动控制技术研究所

电脑开发与应用

影响因子:0.265
ISSN:1003-5850
年,卷(期):2015.(3)
  • 1
  • 5