A 183.4nJ/inference 152.8μW Single-Chip Fully Synthesizable Wired-Logic DNN Processor for Always-On 35 Voice Commands Recognition Application.

VLSI Technology and Circuits(2023)

引用 1|浏览15
暂无评分
摘要
A 183.4nJ/inference single-chip wired-logic DNN processor that is capable of recognizing all 35 commands defined in the industrial standard voice recognition data set (Google Speech Command Dataset) is developed. The fully synthesizable processor recognizes 3.5 times more commands with 1.6 times better energy efficiency than the state-of-the-art analog processor while keeping design cost low. By implementing all the processing circuits and wiring required for the 16-layer DNN onto a single chip (7.63 mm 2 in 40nm), the need to store weight coefficients and intermediate data in DRAM/SRAM is eliminated. Owing to the proposed architecture, a low power consumption of 152.8$\mu$W is achieved, which is low enough for always-on applications on battery-powered IoT devices.
更多
查看译文
关键词
16-layer DNN,3.5 times more commands,35 voice commands recognition application,energy 183.4 nJ,fully synthesizable processor,Google Speech Command Dataset,industrial standard voice recognition data,power 152.8 muW,single chip,size 40.0 nm,state-of-the-art analog processor,wiring
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要