Concept-based Speech Translation

Abstract

As part of the JANUS speech-to-speech translation project, we have developed a robust translation system based on the information structures inherent to the task being performed. The basic premise is that the structure of the information to be transmitted is largely independent of the language used to encode it. Our system performs no syntactic analysis; speaker utterances are parsed into semantic chunks, which can be strung together without grammatical rules, and passed through a simple template-based translation module. We have achieved encouraging coverage rates on English, German and Spanish input with English, German and Spanish output. The concept-based approach to speech parsing and translation described in this paper is especially well-suited to processing of spontaneous speech, which is often ungrammatical and subject to recognition errors.