This work was the final project of our "EEE 212 -Numerical Technique Laboratory" course. We have designed a text-to-speech conversion system in this work.
Language is the ability to express one’s thoughts by means of a set of signs (text), gestures, and sounds. It is a distinctive feature of human beings, who are the only creatures to use such a system. Speech is the oldest means of communication between people and it is also the most widely used. Technology is always moving towards the betterment for human. With that goal in mind, we are planning to make a Text to Speech (TTS) system for the handicapped people who have eye problems and also for the people who are still illiterate and cannot read. We have created a MATLAB Project where we have aimed to solve this problem.
Text-to-speech (TTS) is the generation of synthesized speech from text. Our goal is to make synthesized speech as intelligible, natural and pleasant to listen, as human speech. The quality of a speech synthesizer is judged by its similarity to the human voice and by its ability to be understood.OCR is used to extract characters and symbols from the Text Image without any mistakes, making the software more reliable. It can also extract handwritten as well as printed text into computerreadable text.
Almost all the OCR designs use modification of this basic architecture. Given the text image for recognition, first it is preprocessed for the removal of artifacts and the image is prepared for recognition. It involves binarization, skew correction, normalization, and undergoes image enhancements like filtering out noise and contrast correction. Segmentation is followed by feature extraction, which is concerned with the representation of the object. Feature extraction and classification are the heart of OCR.
