vioft2nntf2t|tblJournal|Abstract_paper|0xf4ff9acf290000004868010001000900
The research presented in this paper is part of an ongoing investigation of speaker identification for Gujarati isolated digit. In our previous work, we evaluated feature extraction method of Gujarati isolated digit for speaker identification using Mel-Frequency Cepstral Coefficient (MFCC). Here we establish on our previous research work for speaker identification of Gujarati isolated digits. The aim of our proposed work is to provide best security or identification to the authentication system which will identify Gujarati speakers. For the projected work we have used MFCC and VQ computation scheme for the Feature extraction and pattern matching techniques. The study also explains about using the technique in brief. For the proposed approach dataset of Gujarati numeral (0 to 10) was recorded from different speakers from different age groups which serve to train and test each speaker speech sample. The distance between each test codeword and each codeword in master codebook is computed. That difference helps in making recognition decision. An experimental evaluation is done using MATLAB simulations. The outcomes indicate that our proposed work of speaker identification system for Gujarati isolated digit achieves good amount of results on our Gujarati digit database with the combination of the proposed technique.