Speech synthesis system using LabVIEW

Abstract

The present work is synthesis of voice signal using LabVIEW with the input of text signal in the form of image file, typed text or pdf. The synthesis of signal based on the Optical Code Recognition (OCR) techniques. Even though already so many technologies available in the synthesis of voice signal, the LabVIEW based system is very user friendly and cost effective. The programming of LabVIEW is graphical based enhances the users to be compatible. The proposed system has two parts such as optical character recognition and text to speech conversion (TTS). The Text to Speech interfaces is provided by Microsoft Speech SDK. In addition to that LabVIEW supports special characters and special language characters. The input of either a text document or written text is read and it is converted into speech signal. The output of an audio file is listened by headset or speaker connected with the processor. The above proposed system of a speech synthesis is very useful for educational purpose, for visually impaired people and for shorthand writing.