Benchmark for Speaker Identification using Linear Prediction Coding (LPC) on Vowels Preceding Nasal Continuants in Kannada

Abstract

The aim of the present study was to obtain the percentage of speaker identification using vowels preceding nasal continuants in Kannada speaking individuals using semi-automatic method. The participants were twenty Kannada speaking adult males in the age range of 21-32 years. The material was meaningful Kannada words containing long vowels /a:/, /i:/ and /u:/ preceding nasal continuants /m/ and /n/ embedded in Kannada sentences. The participants read the material four times each under two conditions (a) live recording and (b) mobile network recording. The target words were truncated using the PRAAT software. Each vowel preceding nasal was subjected for LPC using Speech Science lab workbench for Semi-automatic speaker recognition software. The study was compared under three conditions: (a) Live vs live recording, (b) Mobile network vs mobile network recording and (c) Live vs mobile network recoding. The results of the present study indicated relatively high percent of correct speaker identification using LPC in Live vs Live and Mobile network vs Mobile network conditions compared to Live vs mobile network condition. Thus, the present study provided some proof to examine the efficiency of semi-automatic method using LPC which helps in speaker identification. The obtained results would serve as potential measure in the forensic scenario for Speaker Identification using vowel preceding nasal continuants in Kannada.