论文标题
HOPF物理储层计算机用于可重构的声音识别
Hopf Physical Reservoir Computer for Reconfigurable Sound Recognition
论文作者
论文摘要
HOPF振荡器是一种非线性振荡器，表现出限制周期运动。这款储层计算机利用振荡器的振动性，这使其成为可重新配置的声音识别任务的理想候选者。在本文中，系统地证明了HOPF水库计算机执行声音识别的功能。这项工作表明，与传统方法相比，HOPF储层计算机可以提供较高的声音识别精度（例如，MEL Spectrum +机器学习方法）。更重要的是，HOPF储层计算机作为声音识别系统运行不需要音频预处理，并且具有非常简单的设置，同时仍提供高度的可重构性。这些功能铺平了将物理储层计算应用于低功率边缘设备中声音识别的方式。
The Hopf oscillator is a nonlinear oscillator that exhibits limit cycle motion. This reservoir computer utilizes the vibratory nature of the oscillator, which makes it an ideal candidate for reconfigurable sound recognition tasks. In this paper, the capabilities of the Hopf reservoir computer performing sound recognition are systematically demonstrated. This work shows that the Hopf reservoir computer can offer superior sound recognition accuracy compared to legacy approaches (e.g., a Mel spectrum + machine learning approach). More importantly, the Hopf reservoir computer operating as a sound recognition system does not require audio preprocessing and has a very simple setup while still offering a high degree of reconfigurability. These features pave the way of applying physical reservoir computing for sound recognition in low power edge devices.
