DocumentCode
2964446
Title
One Effective Method to Design LBG Initial Codebook
Author
Yanxia, Liang ; Jiawei, Yang ; Ye, Li
Author_Institution
State Key Lab. Of Integrated Service Networks & Inf. Sci. Inst., Xidian Univ., Xi´´an, China
Volume
2
fYear
2011
fDate
28-29 March 2011
Firstpage
628
Lastpage
631
Abstract
LBG algorithm is commonly used in multidimensional signal processing. It´s one of the most effective methods to generate codebooks. Better initial codebook of LBG algorithm leads to better quality of final codebook. In order to find one effective method to design LBG initial codebook, four design methods of initial codebook for LBG algorithm are compared, including Random method, Splitting method, Most-Dispersed Code words Initialization (MDCI) and Greedy Tree Growing Algorithm (GTGA). The codebooks after LBG algorithm are used to quantize Line Spectral Frequency (LSF) coefficients in speech coding. Simulation by C programming language demonstrates that GTGA is optimal. Because it executes within a sShort span of HtimeH, and both the number of iteration times and run time are close to by splitting method in LBG algorithm. Moreover MSE is minor and Average Spectral Distortion is small.
Keywords
mean square error methods; signal processing; speech coding; vector quantisation; C programming language; LBG initial codebook; Linde-Buzo-Gray algorithm; MSE; average spectral distortion; greedy tree growing algorithm; line spectral frequency coefficient; most-dispersed code word initialization; multidimensional signal processing; random method; speech coding; splitting method; Algorithm design and analysis; Radio access networks; Signal processing algorithms; Speech; Training; Variable speed drives; Vector quantization; LBG algorithm; Mean Squared Error; Spectral Distortion; initial codebook; signal processing; vector quantization;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Computation Technology and Automation (ICICTA), 2011 International Conference on
Conference_Location
Shenzhen, Guangdong
Print_ISBN
978-1-61284-289-9
Type
conf
DOI
10.1109/ICICTA.2011.442
Filename
5750967
Link To Document