Design of Gujarati Text-to-Speech System

Abstract

In this paper we describe Speech synthesis which also called as Text –to-speech synthesis. The speech synthesized is the artificial generation of human speech from text (Gujarati text). The required database in the conversion of character-to-sound is recorded by PRAAT software and is saved in .wav format in the directory. The smallest segment of the recorded voice is concatenated to produce speech of the desired words. The main aim of using this method is, it is simple. Concatenation technique is used and software used is MATLAB.