论文标题
硬件意识培训，以便在通用和专业硬件上发现有效的关键字。
Hardware Aware Training for Efficient Keyword Spotting on General Purpose and Specialized Hardware
论文作者
论文摘要
关键字斑点（KWS）为许多移动和边缘应用程序（包括手机，可穿戴设备和汽车）提供了关键的用户界面。由于KWS系统通常“始终”，因此最大程度地提高了准确性和功率效率对它们的实用性至关重要。在这项工作中，我们使用硬件意识培训（HAT）来建立基于Legendre Memory单元（LMU）的新KWS神经网络，该网络（LMU）达到了最新的（SOTA）精度和低参数计数。这使神经网络可以在标准硬件（212美元$ $ W）上有效运行。我们还表征了定制设计的加速器硬件的功率要求，该硬件可实现8.79 $μ$ W的SOTA功率效率，通过24倍击败通用低功率硬件（微控制器），而特殊用途ASIC则以16倍的速度击败。
Keyword spotting (KWS) provides a critical user interface for many mobile and edge applications, including phones, wearables, and cars. As KWS systems are typically 'always on', maximizing both accuracy and power efficiency are central to their utility. In this work we use hardware aware training (HAT) to build new KWS neural networks based on the Legendre Memory Unit (LMU) that achieve state-of-the-art (SotA) accuracy and low parameter counts. This allows the neural network to run efficiently on standard hardware (212$μ$W). We also characterize the power requirements of custom designed accelerator hardware that achieves SotA power efficiency of 8.79$μ$W, beating general purpose low power hardware (a microcontroller) by 24x and special purpose ASICs by 16x.
