CMU wearable computers for real-time speech translation

Carnegie Mellon's Wearable Computers Laboratory has built four generations of real-time speech translation wearable computers, culminating in the Spee ch Translator Smart Module. Smart Modules use a family of interoperable mod ules supporting real-time speech recognition, language translation, and spe ech synthesis. In this article we examine the effect of various design fact ors on performance with emphasis on modularity and scalability. A system-le vel approach to power/performance optimization is described that improved t he metric of (performance/(weight * volume * power)) by over a factor of 30 0 through the four generations.