Real time speaker recognition of letter ‘zha’ in Tamil language

Author

Srinivasan, A.

Author_Institution

Dept. of Electron. & Commun. Eng., SASTRA Univ., Kumbakonam, India

fYear

2013

fDate

4-6 July 2013

Firstpage

1

Lastpage

5

Abstract

The aim of this paper is speaker recognition of the letter `zha´ in Tamil language, which consists of comparing a speech signal from an unknown speaker to a known speaker. The speech signals of the letter `zha´ of male and female speakers are recognized by the Vector Quantization (VQ) technique called Mel Frequency Cepstrum Coefficients (MFCC). The recorded sampling frequency was at 16 kHz and the bit rate was at 15450 bits per second, where the original bit rate was at 128K bits per second with the help of wave surfer audio tool. The real time recognized output is taken by using Finite Fourier Transform (FFT) and this result is compared by using Mel Frequency Cepstral coefficients and vector Quantization. The speaker recognition system results are analyzed in MATLAB.

Keywords

Fourier transforms; natural language processing; real-time systems; speaker recognition; FFT; Finite Fourier Transform; MATLAB; MFCC; Tamil language; VQ technique; letter ZHA; mel frequency cepstrum coefficients; real time speaker recognition; recorded sampling frequency; speech signal; vector quantization; Cepstrum; Filter banks; Mel frequency cepstral coefficient; Speaker recognition; Speech; Speech recognition; Vectors; FFT; MATLAB; Mel Frequency Cepstrum Coefficients; Speaker recognition; Tamil Language; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Computing, Communications and Networking Technologies (ICCCNT),2013 Fourth International Conference on

Conference_Location

Tiruchengode

Print_ISBN

978-1-4799-3925-1

Type

conf

DOI

10.1109/ICCCNT.2013.6726857

Filename

6726857