Finite State Transducers Based on k-TSS Grammars for Speech Translation
Finite state transducers can be automatically learnt from bilingual corpus, and they can be easily integrated in an automatic speech recognition system for speech translation applications. In this work we explore the possibility of using k-testable language models to generate translations models. We report speech translation results for one easy and well known task, EuTrans (Spanish-English), and for other similar task, Euskal Turista (Spanish-Basque). Euskal Turista has proved to be a quite difficult task because of the distance between the languages involved.
KeywordsMachine Translation Speech Recognition System Statistical Machine Translation Word Error Rate Automatic Speech Recognition System
Unable to display preview. Download preview PDF.
- 2.Brown, P.F., Della Pietra, S.A., Della Pietra, V.J., Mercer, R.L.: The mathematics of statistical machine translation: Parameter estimation. Computational Linguistics 19, 263–311 (1993)Google Scholar
- 4.Amengual, J., Benedí, J., Casacuberta, F., Castaño, M., Castellanos, A., Jiménez, V., Llorens, D., Marzal, A., Pastor, M., Prat, F., Vidal, E., Vilar, J.: The EuTrans-I speech translation system. Machine Translation 1 (2000)Google Scholar