⚡ 本页包含 AI 生成的分析内容，仅供参考
该论文提出了一种基于脉冲域除法能量（Spike-Domain Divisive Energy）的声学特征提取器，能够在背景噪声和工艺变化下保持鲁棒性，功耗仅为109nW，解决了传统噪声依赖训练方法在不同信噪比和噪声类型下精度下降的问题。
In mobile and edge devices, always-on keyword spotting (KWS) is an essential function to detect wake-up words. Recent works achieved extremely low power dissipation down to ~500nW [1]. However, most of them adopt noise-dependent training, i.e. training for a specific signal-to-noise ratio (SNR) and noise type [1], and therefore their accuracies degrade for different SNR levels and noise types that are not targeted in the training (Fig. 9.9.1, top left). To improve robustness, so-called noise-independent training can be considered, which is to use the training data that includes all the possible SNR levels and noise types [2]. But, this approach is challenging for an ultra-low-power device since it demands a large neural network to learn all the possible features. A neural network of a fixed size has its own memory capacity limit and reaches a plateau in accuracy if it has to learn more than its limit (Fig. 9.9.1, top right). On the other hand, it
Dewei Wang, Sung Justin Kim, Minhao Yang, Aurel A. Lazar, Mingoo Seok
Columbia University, New York, NY