Francisco Casacuberta, David Llorens, Carlos D. Martínez-Hinarejos, Sirko Molau, Francisco J. Nevado, Hermann Ney, Moisés Pastor-i-Gadea, David Picó, Alberto Sanchis, Enrique Vidal, Juan M. Vilar. Speech-to-speech translation based on finite-state transducers. International Conference on Acoustic, Speech and Signal Processing, 2001. IEEE Press.

Nowadays, the most successful speech recognition systems are based on stochastic finite-state networks (hidden Markov models and n-grams). Speech translation can be accomplished in a similar way as speech recognition. Stochastic finite-state transducers, which are specific stochastic finite-state networks, have proved very adequate for translation modeling. In this work a speech-to-speech translation system, the sc EuTrans system, is presented. The acoustic, language and translation models are finite-state networks that are automatically learnt from training samples. This system was assessed in a series of translation experiments from Spanish to English and from Italian to English in an application involving the interaction (by telephone) of a customer with a receptionist at the front-desk of a hotel.