Speech Recognition of the letter 'zha' in Tamil Language using HMM

TL;DR

This paper presents a method for recognizing the Tamil letter 'zha' using Hidden Markov Models trained on LPC-coded speech signals from multiple speakers, demonstrating a novel approach in Tamil speech recognition.

Contribution

It introduces an improved LPC coding combined with HMM for recognizing the Tamil letter 'zha', a novel application in Tamil speech processing.

Findings

Successful LPC coding at reduced bit rate

Implementation of HMM for letter recognition

Potential for improved Tamil speech recognition systems

Abstract

Speech signals of the letter 'zha' in Tamil language of 3 males and 3 females were coded using an improved version of Linear Predictive Coding (LPC). The sampling frequency was at 16 kHz and the bit rate was at 15450 bits per second, where the original bit rate was at 128000 bits per second with the help of wave surfer audio tool. The output LPC cepstrum is implemented in first order three state Hidden Markov Model(HMM) chain.