Interspeech'2005 - Eurospeech
This paper focuses on the interface between speech recognition and machine translation in a speech translation system. Based on a thorough theoretical framework, we exploit word lattices of automatic speech recognition hypotheses as input to our translation system which is based on weighted finite-state transducers. We show that acoustic recognition scores of the recognized words in the lattices positively and significantly affect the translation quality. In experiments, we have found consistent improvements on three different corpora compared with translations of single best recognized results. In addition we build and evaluate a fully integrated speech translation model.
Bibliographic reference. Matusov, E. / Kanthak, S. / Ney, Hermann (2005): "On the integration of speech recognition and statistical machine translation", In INTERSPEECH-2005, 3177-3180.