A Fast Network Exploration Strategy to Profile Low Energy Consumption for Keyword Spotting
This work addresses energy-efficient deployment for keyword spotting on smart devices, offering an incremental optimization for hardware-specific configurations.
The paper tackles the challenge of configuring neural networks for keyword spotting to meet accuracy and hardware deployment needs, proposing a regression-based exploration technique that scales filters and quantizes layers, resulting in at least 2.1x and 4x improvements in energy and energy efficiency on FPGA compared to recent implementations.
Keyword Spotting nowadays is an integral part of speech-oriented user interaction targeted for smart devices. To this extent, neural networks are extensively used for their flexibility and high accuracy. However, coming up with a suitable configuration for both accuracy requirements and hardware deployment is a challenge. We propose a regression-based network exploration technique that considers the scaling of the network filters ($s$) and quantization ($q$) of the network layers, leading to a friendly and energy-efficient configuration for FPGA hardware implementation. We experiment with different combinations of $\mathcal{NN}\scriptstyle\langle q,\,s\rangle \displaystyle$ on the FPGA to profile the energy consumption of the deployed network so that the user can choose the most energy-efficient network configuration promptly. Our accelerator design is deployed on the Xilinx AC 701 platform and has at least 2.1$\times$ and 4$\times$ improvements on energy and energy efficiency results, respectively, compared to recent hardware implementations for keyword spotting.