TEXT PICTURE TRANSLATION INTO SPEECH IN DESIRED LANGUAGE

Text to speech is a technology through which computer is made to speak. If a study is performed like listening or reading and which is more effective definitely answer is listening, because people will understand more by listening than reading. In many research(s) it is proved that listening improves imagination power. The main aim is to provide speech output in real time for blind people when they gave printed text as input. This text to speech requires two technologies; Optical Character Recognition (OCR) and text to speech conversion. The former technique is used for extracting text from image. The later technology converts the extracted text into speech. In any reading assistant system, the first and important function is text information extraction and this is the integral part of OCR. To recognize words OCR is used.