Title :
The binary vector quantization
Author :
Yan, Long-Jhe ; Hwang, Shaw-Hwa
Author_Institution :
Dept. of Electr. Eng., Nat. Taipei Univ. of Technol., Taipei
Abstract :
The binary search algorithm for vector quantization is firstly proposed in this paper. It employs jointly sensitive-codeword based on the binary tree search structure to improve the search structure. Comparisons of experimental results show that the proposed algorithm performs the best. Most of search space is reduced. In the case of G.729´s LSP quantization, more than 58% of search space is reduced.
Keywords :
rate distortion theory; tree searching; vector quantisation; VQ encoding; binary tree search algorithm; binary vector quantization; jointly sensitive-codeword; rate distortion performance; Binary trees; Clustering algorithms; Decoding; Distortion measurement; Encoding; Image coding; Partitioning algorithms; Space technology; Speech; Vector quantization; TSVQ; VQ; binary VQ (BVQ); jointly sensitive-codeword;
Conference_Titel :
Communications, Control and Signal Processing, 2008. ISCCSP 2008. 3rd International Symposium on
Conference_Location :
St Julians
Print_ISBN :
978-1-4244-1687-5
Electronic_ISBN :
978-1-4244-1688-2
DOI :
10.1109/ISCCSP.2008.4537296
