Speech translation based on automatically trainable finite-state models
Juan Carlos Amengual, José-Miguel Benedí, Klaus Beulen, Francisco Casacuberta, Asunción Castaño, Antonio Javier Martín Castellanos, Victor M. Jimenez, David Llorens, Andrés Marzal, Hermann Ney, Federico Prat, Enrique Vida, Juan Miguel Vila · 1997
This paper extends previous work exploring the use of Subsequential Transducers to perform speech-input translation in limited-domain tasks. This is done following an integrated approach in which a Subsequential Transducer replaces the input-language model of a conventional speech recognition system, and is used both as language and translation model. This way, the search for the recognised sentence also produces the corresponding translation. A corpus-based approach is adopted in order to build the required models from training data. Experimental results are presented for the translation task considered in the EUTRANS project: one in the hotel domain with more than 500 words per language and language perplexities near to 10.