Sistema de Traducción Oral para el Castellano, Catalán e Inglés

This paper describes the FAME Interlingua-based Speech-to-Speech Translation System for Catalan, English and Spanish. This is an extension of the already existing NESPOLE! that translates between English, French, German and Italian, but all modules have now been integrated in an Open Agen Architecture. This article describes the system architecture and the interlingua formalism used, called Interchange Format (IF). In what follows we describe the components of the translation module including the speech recognizer, the analysis chain, the generation chain and the speech synthesizer. We also show the results obtained from an evaluation of the system