A 510-nW Wake-Up Keyword-Spotting Chip Using Serial-FFT-Based MFCC and Binarized Depthwise Separable CNN in 28-nm CMOS

摘要

We propose a sub-mu W always- ON keyword spotting (mu KWS) chip for audio wake-up systems. It is mainly composed of a neural network (NN) and a feature extraction (FE) circuit. For significantly reducing the memory footprint and computational load, four techniques are used to achieve ultralow-power consumption: 1) a serial-FFT-based Mel-frequency cepstrum coefficient circuit is designed for FE, instead of the common parallel FFT. 2) A small-sized binarized depthwise separable convolutional NN (DSCNN) is designed as the classifier. 3) A framewise incremental computation technique is devised in contrast to the conventional whole-word processing. 4) Reduced computation allows a low system clock frequency, which enables near-threshold voltage operation, and low leakage memory blocks are designed to minimize the leakage power. Implemented in 28-nm CMOS technology, this mu KWS consumes 0.51 mu W at a 40-kHz frequency and a 0.41-V supply, with an area of 0.23 mm(2). Using the Google speech command data set, 97.3% accuracy is reached for a one-word KWS task and 94.6% for a two-word task.