Keyword spotting has gained popularity as a natural way to interact with consumer devices in recent years. However, because of its always-on nature and the variety of speech, it necessitates a low-power design as well as user customization. This paper describes a low-power, energy-efficient keyword spotting accelerator with SRAM based in-memory computing (IMC) and on-chip learning for user customization. However, IMC is constrained by macro size, limited precision, and non-ideal effects. To address the issues mentioned above, this paper proposes bias compensation and fine-tuning using an IMC-aware model design. Furthermore, because learning with low-precision edge devices results in zero error and gradient values due to quantization, this paper proposes error scaling and small gradient accumulation to achieve the same accuracy as ideal model training. The simulation results show that with user customization, we can recover the accuracy loss from 51.08\% to 89.76\% with compensation and fine-tuning and further improve to 96.71\% with customization. The chip implementation can successfully run the model with only 14$uJ$ per decision. When compared to the state-of-the-art works, the presented design has higher energy efficiency with additional on-chip model customization capabilities for higher accuracy.
翻译:近些年来,关键字点字作为与消费者设备互动的一种自然方式越来越受欢迎,然而,由于它总是在性质上而且言语多样,它需要低功率设计和用户定制。本文描述了一个低功率、节能关键字点点点加速器,它以模拟计算(IMC)和芯片学习为基础,以进行用户定制。然而,IMC受到宏观规模、有限精确度和非理想效应的限制。为了解决上述问题,本文件建议使用IMC-aware模型设计来进行偏差补偿和微调。此外,由于低精度边缘装置的学习导致零误差和因四分化而导致的梯度值。本文还介绍了一个低能、节能关键字点点点点点点点点点加速器,以达到与理想模型培训相同的精确度。模拟结果表明,根据用户定制,我们可以收回51.08 ⁇ 至89.76 ⁇ 的准确度损失,同时进行补偿和微调整,并进一步改进到96.71 ⁇ 的定制。芯片实施可以成功运行模型,每项只有14.J美元,每项。与最新设计效率相比,可实现更高的设计效率。