摘要
This brief presents an event-driven keyword spotting (KWS) system for reducing the significant but usually ignored energy dissipations on the &null A/D converter and microphone. &null energy per inference&null and &null responsiveness&null are new design goals of such KWS engine. A 7-layer 1-dimensional binarized convolutional neural network (1D-BCNN) was designed to achieve 95% inference accuracy for detecting 10 keywords, plus silence and unknown, from raw speech, and 64 32-element signed binary inner product units were allocated in the engine to deliver the 4,096 operations/cycle maximum throughput. The 16nm implementation consumes only 0.1mm2 silicon area and 5&null energy (including memory accesses), while achieving 1.72ms response time. The performance is comparable to state-of-the-art KWS designs without sacrificing number of detectable keywords or inference accuracy.