Answers are grounded in this paper and cite their sources.
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 4×. The NN processor employs computational sprinting, enabling 12× 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.
No takes yet. Share an insight, caveat, or question.
Oh et al. (2019) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: