CMU wearable computers for real-time speech translation

Abstract

Carnegie Mellon's Wearable Computers Laboratory has built four generations of real-time speech translation wearable computers, culminating in the Speech Translator Smart Module. Smart Modules are a family of interoperable modules supporting real-time speech recognition, language translation, and speech synthesis. In this paper, we examine the effect of various design factors on performance with emphasis on modularity and scalability. A system-level approach to power / performance optimization is described that improved the metric of (performance / (weight * volume * power)) by over a factor of 300 through the four generations.

System design approach to power aware mobile computers

“…For most generations of CMU wearable computers, we have performed extensive power management and optimization research, and Figure 1 shows just several of these examples [1,6,7,8].…”

“…In the long term, a system-level approach to power/performance optimization will be a crucial catalyst for making mobile/wearable computers an everyday tool for the general public [1]. Energy efficiency must be considered in all phases of system design.…”