AUTOMATIC SPEECH RECOGNITION TO CORRECT QURANIC PHONEME

Abstract

The objective of this project is to develop speech recognition system to recognize Quranic phoneme while reciting and suggest corrections. This report explores different techniques used for the recognition of the recitation of the Holy Quran. Different stages like input, acoustic modelling etc will be studied and discussed. Finally the end product of the project will be an software recognizing recitation of the Holy Quran and suggesting corrections after being trained for a specific user. This project uses sphinx framework which is based upon the statistical approach , the Hidden Markov Models (HMMs) to develop the software. The main advantage of using this technique is that it provides a simple and flexible mechanism for modelling sequences of variable length [1]. Broadly speaking, the mechanism of the system begins when a user speaks and the spoken word or utterance is recognized by the system automatically. The quality of a speech recognition system is usually measured for its accuracy [4], Depending upon the accuracy the corrections will be suggested.