This paper introduces, to the best of the authors' knowledge, the first
fine-grained temporal sparsity-aware keyword spotting (KWS) IC leveraging
temporal similarities between neighboring feature vectors extracted from input
frames and network hidden states, eliminating unnecessary operations and memory
accesses. This KWS IC, featuring a bio-inspired delta-gated recurrent neural
network ({\Delta}RNN) classifier, achieves an 11-class Google Speech Command
Dataset (GSCD) KWS accuracy of 90.5% and energy consumption of 36nJ/decision.
At 87% temporal sparsity, computing latency and energy per inference are
reduced by 2.4$\times$/3.4$\times$, respectively. The 65nm design occupies
0.78mm$^2$ and features two additional blocks, a compact 0.084mm$^2$ digital
infinite-impulse-response (IIR)-based band-pass filter (BPF) audio feature
extractor (FEx) and a 24kB 0.6V near-Vth weight SRAM with 6.6$\times$ lower
read power compared to the standard SRAM.

这篇论文介绍了一种基于时间稀疏性的细粒度关键词检测技术，它利用输入帧的特征向量和网络隐藏状态之间的时间相似性，消除了不必要的操作和内存访问。该技术采用了生物启发式的 Delta 门控循环神经网络（ΔRNN）分类器，在 Google 语音指令数据集（GSCD）上实现了 90.5% 的检测准确率和 36nJ / 决策的能量消耗。在 87% 的时间稀疏率下，推理的计算延迟和能量消耗分别减少了 2.4 倍和 3.4 倍。该设计占据了 0.78mm² 的面积，还包括两个附加模块，其中一个是 0.084mm² 的紧凑型基于无限脉冲响应（IIR）的带通滤波器（BPF）音频特征提取器（FEx），另一个是 24kB、0.6V 的近阈值权重 SRAM，其读取功耗比标准 SRAM 低 6.6 倍。