This paper proposes a hardware-efficient architecture, Linearized Convolution
Network (LiCo-Net) for keyword spotting. It is optimized specifically for
low-power processor units like microcontrollers. ML operators exhibit
heterogeneous efficiency profiles on power-efficient hardware. Given the exact
theoretical computation cost, int8 operators are more computation-effective
than float operators, and linear layers are often more efficient than other
layers. The proposed LiCo-Net is a dual-phase system that uses the efficient
int8 linear operators at the inference phase and applies streaming convolutions
at the training phase to maintain a high model capacity. The experimental
results show that LiCo-Net outperforms single-value decomposition filter (SVDF)
on hardware efficiency with on-par detection performance. Compared to SVDF,
LiCo-Net reduces cycles by 40% on HiFi4 DSP.

本文提出了一种硬件有效的架构，Linearized Convolution Network（LiCo-Net），专门为微控制器等节能处理器单元进行关键字识别。在推理阶段使用高效的 int8 线性运算符，在训练阶段应用流式卷积以保持模型容量高，实验结果表明，LiCo-Net 在硬件效率方面优于单值分解滤波器（SVDF），检测性能相当。与 SVDF 相比，LiCo-Net 在 HiFi4 DSP 上减少了 40％的周期。

LiCo-Net: 基于线性化卷积的硬件高效关键词检测网络

LiCo-Net: Linearized Convolution Network for Hardware-efficient Keyword Spotting

A low-power precision-scalable processor for ConvNets or convolutional neural
networks (CNN) is implemented in a 40nm technology. Its 256 parallel processing
units achieve a peak 102GOPS running at 204MHz. To minimize energy consumption
while maintaining throughput, this works is the first to both exploit the
sparsity of convolutions and to implement dynamic precision-scalability
enabling supply- and energy scaling. The processor is fully C-programmable,
consumes 25-288mW at 204 MHz and scales efficiency from 0.3-2.6 real TOPS/W.
This system hereby outperforms the state-of-the-art up to 3.9x in energy
efficiency.

该研究实现了一种低功耗、可精确可扩展的卷积神经网络处理器，其充分利用卷积的稀疏性和动态精度可扩展性，实现了供应和能量缩放，能够在保持吞吐量的情况下最小化能量消耗，同时其实现的效率从 0.3-2.6 实际 TOPS/W，超越了同类产品达到 3.9 倍的能效。