IoT chip-oriented multi-level voice intelligent awakening method and system

Abstract

The invention provides an IoT chip-oriented multi-level voice intelligent awakening method and system. The method comprises the following steps: S1, when to-be-processed voice is acquired, executing S2; S2, judging whether the to-be-processed voice meets a first preset condition or not; when the to-be-processed voice meets the first preset condition, executing S3; otherwise, ending awakening; S3,judging whether the to-be-processed voice meeting the first preset condition meets a second preset condition or not; if yes, executing S4; otherwise, ending awakening; S4, judging whether the to-be-processed voice meeting the first preset condition and the second preset condition meets a third preset condition or not; if yes, executing S5; otherwise, ending awakening; and S5, comprehensively awakeing the IoT chip. According to the IoT chip-oriented multi-level voice intelligent awakening method provided by the invention, the awakening system is graded, and a step-by-step awakening and step-by-step power-on mechanism is adopted, so that the false awakening rate of the whole chip is reduced, and the overall power consumption of the chip is greatly reduced.

Description

technical field [0001] The present invention relates to the field of wake-up technology, in particular to a multi-level voice intelligent wake-up method and system for IoT chips. Background technique [0002] At present, according to the startup process of the chip, the IoT chip is generally divided into two large power domains. The first power domain is for waking up the system, and the second power domain is for all other parts of the chip except for waking up the system. After the chip is powered on, the wake-up system of the chip starts to work. At this time, only the first power domain has power. Only after the wake-up system detection is passed will the second power domain be powered on, so that the entire chip is in a working state. [0003] The wake-up system of existing IoT chips only includes energy detection technology, that is, when a sound is detected that exceeds a certain energy threshold, the entire chip will be activated for sound recognition. At this time,...

AI Technical Summary

Problems solved by technology

[0003]The wake-up system of existing IoT chips only includes energy detection technology, that is, when a sound exceeds a certain energy threshold, it will start the entire chip for sound recognition, and this The input voice may not be a human voice or a human voice but not the wake-up word of the device. In both cases, the entire chip will be awakened by mistake, and the probability of these two cases in actual applications is very high, so The overall power consumption of the chip is higher

Images