BMRUs enable a direct one-to-one mapping from learned parameters to current-mode analog circuit elements, with discrete hysteretic outputs suppressing noise by at least 20x and supporting sub-microwatt RNN inference in 180 nm CMOS simulations.
Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Keyword spotting (KWS) constitutes a major component of human-technology interfaces. Maximizing the detection accuracy at a low false alarm (FA) rate, while minimizing the footprint size, latency and complexity are the goals for KWS. Towards achieving them, we study Convolutional Recurrent Neural Networks (CRNNs). Inspired by large-scale state-of-the-art speech recognition systems, we combine the strengths of convolutional layers and recurrent layers to exploit local structure and long-range context. We analyze the effect of architecture parameters, and propose training strategies to improve performance. With only ~230k parameters, our CRNN model yields acceptably low latency, and achieves 97.71% accuracy at 0.5 FA/hour for 5 dB signal-to-noise ratio.
fields
cs.AR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations
BMRUs enable a direct one-to-one mapping from learned parameters to current-mode analog circuit elements, with discrete hysteretic outputs suppressing noise by at least 20x and supporting sub-microwatt RNN inference in 180 nm CMOS simulations.