Volume : II, Issue : IV, April - 2013

Automatic Indian Language Identification

P. Vijay Kumar, A. Raviteja

Abstract :

Automatic Language Identification (ALID) has been for a long time an active research area with a large variety of applications in human-computer intelligent interaction. The most used technique in this field is the Hidden Markov Models (HMMs) which is a statistical and extremely powerful method. The HMM model parameters are crucial information in HMMoptimizing HMM parameters is still an important and challenging work in LID research area.Usually the Baum-Welch (B-W) Algorithm is used to calculatethe HMM model parameters. However, the B-W algorithm usesan initial random guess of the parameters, therefore afterconvergence the output tends to be close to this initial value of thealgorithm, which is not necessarily the global optimum of themodel parameters. In this paper, MFCC featurescombined with Baum-Welch is proposed; the idea is touse MFCC as input to HMM and to identify the language

Keywords :

HMM   LID   MFCC   Training   LPC  

Article: Download PDF   DOI : 10.36106/ijsr  

Cite This Article:

P. Vijay Kumar,A. Raviteja Automatic Indian Language Identification International Journal of Scientific Research, Vol.II, Issue.IV April 2013


Number of Downloads : 192


References :