This article presents a voice and acoustic activity detector that uses a mixer-based architecture and ultra-low-power neural network (NN)-based classifier. By sequentially scanning 4 kHz of frequency bands and down-converting to below 500 Hz, feature extraction power consumption is reduced by 4x. The NN processor employs computational sprinting, enabling 12x power reduction. The system also features inaudible acoustic signature detection for intentional remote silent wakeup of the system while re-using a subset of the same system components. The measurement results achieve 91.5%/90% speech/non-speech hit rates at 10-dB SNR with babble noise and 142-nW power consumption. Acoustic signature detection consumes 66 nW, successfully detecting a signature 10 dB below the noise level.
Acoustic sensing is one of the most widely used sensing modalities to intelligently assess the environment. In particular, ultra-low power (ULP) always-on voice activity detection (VAD) is gaining attention as an enabling technology for IoT platforms. In many practical applications, acoustic events-of-interest occur infrequently. Therefore, the system power consumption is typically dominated by the always-on acoustic wakeup detector, while the remainder of the system is power-gated the vast majority of the time. A previous acoustic wakeup detector [1] consumed just 12nW but could not process voice signals (up to 4kHz bandwidth) or handle non-stationary events, which are essential qualities for a VAD. Prior VAD ICs [2,3] demonstrated reliable performance but consumed significant power (>20μW) and lacked an analog frontend (AFE), which further increases power. Recent analog-domain feature extraction-based VADs [4,5] also reported μW-level power consumption, and their simple decision tree [4] or fixed neural network-based approach [5] limited broader use for various acoustic event targets. In summary, no sub-μW VAD has been reported to date, preventing the use of VADs in unobtrusive mm-scale sensor nodes.