Text to speech, a rewriting system approach

Abstract

In this document we present an open source text-to-speech for Portuguese. Our first goal is to provide a flexible way to extend it, using a generic way to convert Portuguese words into SAMPA phonemes, and consult dictionaries only on exceptions. The text-to-speech is composed of five layers, each one based on simple rules in a way that can be easily tuned. In order to do that, we wrote a generic text rewriting system that is presented the section 2. The result of this work is a tool that can be used as an independent text-to-speech system or as a natural language processing library for various tasks. We present some examples on how they can be used in the Applications section.