Research Article

Performance Comparison of Speaker Recognition using Vector Quantization by LBG and KFCG

by  Ms. Vaishali Kulkarni, Dr. H. B. Kekre
journal cover
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 3 - Issue 10
Published: July 2010
Authors: Ms. Vaishali Kulkarni, Dr. H. B. Kekre
10.5120/773-1086
PDF

Ms. Vaishali Kulkarni, Dr. H. B. Kekre . Performance Comparison of Speaker Recognition using Vector Quantization by LBG and KFCG. International Journal of Computer Applications. 3, 10 (July 2010), 32-37. DOI=10.5120/773-1086

                        @article{ 10.5120/773-1086,
                        author  = { Ms. Vaishali Kulkarni,Dr. H. B. Kekre },
                        title   = { Performance Comparison of Speaker Recognition using Vector Quantization by LBG and KFCG },
                        journal = { International Journal of Computer Applications },
                        year    = { 2010 },
                        volume  = { 3 },
                        number  = { 10 },
                        pages   = { 32-37 },
                        doi     = { 10.5120/773-1086 },
                        publisher = { Foundation of Computer Science (FCS), NY, USA }
                        }
                        %0 Journal Article
                        %D 2010
                        %A Ms. Vaishali Kulkarni
                        %A Dr. H. B. Kekre
                        %T Performance Comparison of Speaker Recognition using Vector Quantization by LBG and KFCG%T 
                        %J International Journal of Computer Applications
                        %V 3
                        %N 10
                        %P 32-37
                        %R 10.5120/773-1086
                        %I Foundation of Computer Science (FCS), NY, USA
Abstract

In this paper, two approaches for speaker Recognition based on Vector quantization are proposed and their performances are compared. Vector Quantization (VQ) is used for feature extraction in both the training and testing phases. Two methods for codebook generation have been used. In the 1st method, codebooks are generated from the speech samples by using the Linde-Buzo-Gray (LBG) algorithm. In the 2nd method, the codebooks are generated using the Kekre’s Fast Codebook Generation (KFCG) algorithm. For speaker identification, the codebook of the test sample is similarly generated and compared with the codebooks of the reference samples stored in the database. The results obtained for both the methods have been compared. The results show that KFCG gives better results than LBG.

References
Index Terms
Computer Science
Information Sciences
No index terms available.
Keywords

Vector Quantization (VQ) Code Vectors Code Book Euclidean distance

Powered by PhDFocusTM