SIRAGI internals

Support of braille displays: based on libbraille.

Speech synthesis: uses two modules, TTS (Text-to-Speech) and voice synthesis. TTS trnasforms a text to a phonetic string and the voice synthesis transforms phonetic strings into voices. Our TTS is based on Euler. Voice synthesis is based on MBROLA

SIRAGI-OCR classification: the classification of characters uses a neural network generated by Stuttgart Neural Network Simulator.

Developpement library and language: QT/C++ under GNU/Linux and Windows.

What's SIRAGI ?

FAQ