论文标题
LICO-NET：用于硬件有效关键字点的线性化卷积网络
LiCo-Net: Linearized Convolution Network for Hardware-efficient Keyword Spotting
论文作者
论文摘要
本文提出了用于关键字点的硬件效率架构，线性化的卷积网络（LICO-NET）。它专门针对小功率处理器单元（如微控制器）进行了优化。 ML操作员在强力硬件上展示了异质效率概况。鉴于确切的理论计算成本，INT8运算符比浮点运算符更有效，而线性层通常比其他层更有效。提出的LICO-NET是一个双相系统，在推理阶段使用有效的INT8线性操作员，并在训练阶段应用流汇集以保持高模型容量。实验结果表明，LICO-NET在硬件效率方面的表现优于单值分解过滤器（SVDF），并且具有PAR检测性能。与SVDF相比，LICO-NET在HIFI4 DSP上降低了40％的周期。
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.
