Connectionist and Symbolic Processing in Speech-to-Speech Translation: The JANUS System

We present JANUS, a speech-to-speech translation system that utilizes diverse processing strategies including connectionist learning, traditional AI knowledge representation approaches, dynamic programming, and stochastic techniques. JANUS translates continuously spoken English utterances into Japanese and German speech utterances. The overall system performance on a corpus of conference registration conversations is 87%. Two versions of JANUS are compared: one using an LR parser (JANUS-LR) and one using a neural-network based parser (JANUS-NN). Performance results are mixed, with JANUS-LR deriving benefit from a tighter language model and JANUSNN benefiting from greater flexibility.