An Ultra-low Power RNN Classifier for Always-On Voice Wake-Up Detection Robust to Real-World Scenarios
This addresses the need for energy-efficient, robust voice wake-up detection in real-world applications like smart devices, representing a strong specific gain rather than a broad paradigm shift.
The paper tackles the problem of high power consumption in always-on voice wake-up sensors by developing an ultra-low power RNN classifier that achieves less than 3% No Trigger Rate with a duty cycle under 1% in challenging real-world noise conditions, consuming only 45 nW for the RNN.
We present in this paper an ultra-low power (ULP) Recurrent Neural Network (RNN) based classifier for an always-on voice Wake-Up Sensor (WUS) with performances suitable for real-world applications. The purpose of our sensor is to bring down by at least a factor 100 the power consumption in background noise of always-on speech processing algorithms such as Automatic Speech Recognition, Keyword Spotting, Speaker Verification, etc. Unlike the other published approaches, we designed our wake-up sensor to be robust to unseen real-world noises for realistic levels of speech and noise by carefully designing the dataset and the loss function. We also specifically trained it to mark only the speech start rather than adopting a traditional Voice Activity Detection (VAD) approach. We achieve less than 3% No Trigger Rate (NTR) for a duty cycle less than 1% in challenging background noises pooled using a model of an analogue front-end. We demonstrate the superiority of RNNs on this task compared to the other tested approaches, with an estimated power consumption of 45 nW for the RNN itself in 65nm CMOS and a minimal memory footprint of 0.52 kB.