Design Of An Automatic Speaker Recognition System Using MFCC, Vector Quantization And LBG Algorithm

Journal Title: International Journal on Computer Science and Engineering - Year 2011, Vol 3, Issue 8

Abstract

The results of a case study carried out while developing an automatic speaker recognition system are presented in this paper. The Vector Quantization (VQ) approach is used for mapping vectors from a large vector space to a finite number of regions in that space. Each region is called a cluster and can be represented by its center called a codeword. The collection of all codewords is called a codebook. After the enrolment session, the acoustic vectors extracted from input speech of a speaker provide a set of training vectors. LBG algorithm due to Linde, Buzo and Gray is used for clustering a set of L training vectors into a set of M codebook vectors. For comparison purpose, the distance between each test codeword and each codeword in the master codebook is computed. The difference is used to make recognition decision. The entire coding was done in MATLAB and the system was tested for its reliability.

Authors and Affiliations

Prof. Ch. Srinivasa Kumar , Dr. P. Mallikarjuna Rao

Keywords

Related Articles

An Evident Theoretic Feature Selection Approach for Text Categorization

With the exponential growth of textual documents available in unstructured form on the Internet, feature selection approaches are increasingly significant for the preprocessing of textual documents for automatic text cat...

An Efficient and Robust Metacrawler with Parallel Activities

This paper presents the Metacrawler, a fielded Web service at represents the next level up in the information ``food hain.'' he Metacrawler provides a single, central interface for Web cument searching. Upon receiving a...

The efficiency of algorithms DATA MINING "Close + and Extraction of association rules" for indexation 2D/3D and Selection of characteristic views.

This paper presents a new classification and search method of 3D object features views. This method is an application of algorithms:  Close+ for an object views classification purpose  Algorithm for extracting asso...

A COMPARATIVE STUDY OF FUZZY MODELS IN DOCUMENT CLUSTERING

The availability of large quantity of text documents from the World Wide Web and business document management systems has made the dynamic separation of texts into new categories as a very important task for every busine...

MOEMS Ring Resonators and Waveguides an Optical Approach

WDM networks use high speed MOEMS ring resonators. Due to the substrate loss the regular tuning of the rings is not possible, hence we need a specialized tuning element for the same. As the advantages increases so does t...

Download PDF file
  • EP ID EP124428
  • DOI -
  • Views 138
  • Downloads 0

How To Cite

Prof. Ch. Srinivasa Kumar, Dr. P. Mallikarjuna Rao (2011). Design Of An Automatic Speaker Recognition System Using MFCC, Vector Quantization And LBG Algorithm. International Journal on Computer Science and Engineering, 3(8), 2942-2954. https://europub.co.uk./articles/-A-124428