Hardware aware training for efficient keyword spotting on general purpose and specialized hardware
Research posted Sep 09, 2020 by Peter Blouw, Gurshaant Malik, Benjamin Morcos, Aaron R. Voelker and Chris Eliasmith
Keyword spotting (KWS) provides a critical user interface for many mobile and edge applications, including phones, wearables, and cars. As KWS systems are typically ‘always on’, maximizing both accuracy and power efficiency are central to their utility. In this work we use hardware aware training (HAT) to build new KWS neural networks based on the Legendre Memory Unit (LMU) that achieve state-of-the-art (SotA) accuracy and low parameter counts. This allows the neural network to run efficiently on standard hardware (212 μW). We also characterize the power requirements of custom designed accelerator hardware that achieves SotA power efficiency of 8.79 μW, beating general purpose low power hardware (a microcontroller) by 24x and special purpose ASICs by 16x.