Moving speech recognition from software to silicon: the in silico vox project

Abstract

To achieve much faster decoding, or much lower power consumption, we need to liberate speech recognition from the artificial constraints of its current software-only form, and move the essential computations directly into silicon. There are vast efficiencies waiting to be unlocked in this application - we need the proper architecture to do so. We report results from a first-generation hardware architecture simulated at bit-level, and a complete, working FPGA-based prototype. Simulation results show that rather modest hardware designs, running 10-20X slower than conventional processors, can already decode at 0.6 xRT, running the standard 5K Wall Street Journal benchmark.