High-quality Speech Translation for Language Learning
Chao Wang, Stephanie Seneff · 2004
In this paper, we describe a translation framework aimed at achieving high-quality speech translation within restricted conversational domains. Towards this goal, we developed an interlingua-based approach, in which a generation-based method is augmented with an examplebased method to improve system robustness, even with imperfect inputs due to speech recognition errors. The framework is integrated into a dialogue-based language tutoring system, to provide immediate translation assistance to students during the dialogue interaction. We evaluated the translation quality within a weather information domain configured for native English speakers practicing Mandarin Chinese. We achieved perfect or acceptable translations for 94.3 % of the manual transcriptions of a test set of 695 spoken queries, and 90.2% on automatic speech recognition outputs. 1