text to speach system

A text-to-speech system or engine is a collection of two parts: a front-end and a back-end. The first one which generally takes the information that is the input in forms of text. Then the next takes the symbolic linguistic representation as input and outputs the synthesized speech waveform. There are two major tasks in the front-and, one to take the raw text and convert things like numbers and abbreviations into their written-out word equivalents. This procedure is known as the text normalization, pre-processing, or tokenization. Then the next is the process of assigning phonetic transcriptions to words is called text normalization.