Abstract :
In the speech and language research community, the term “speech synthesis” is normally used to describe the process of a computer generating artificial speech from a linguistic input. Nearly always, the linguistic input is text or some sort of text annotated with additional linguistic information. We illustrate the workings of a basic text to speech system. Commonly, such systems operate using a set of distinct modules which operate in a chain, with one module´s output being used as the next module´s input
