System and method for efficient power supply

The present disclosure provides methods and systems for power regulation in a speech recognition system on a chip (SoC). The method includes providing a first voltage to a drain of the first transistor array; coupling an output of a first digital controller to a gate of the first transistor array; coupling a source of the first transistor array to a first power domain to provide a second voltage to the first power domain; comparing the second voltage with a reference voltage; and adjusting a second voltage provided to the first power domain to a preset voltage level based on the comparison result. 本公开提供了用于语音识别片上系统(SoC)中的功率调节的方法和系统。该方法包括向第一晶体管阵列的漏极提供第一电压；将第一数字控制器的输出耦接到所述第一晶体管阵列的栅极；将所述第一晶体管阵列的源极耦接到第一功率域以向所述第一功率域提供第二电压；将所述第二电压与参考电压进行比较；基于所述比较结果，将提供给所述第一功率域的第二电压调节在预设电压电平。