Voice wake-up method, device, computer equipment and storage medium

Abstract

The invention relates to a voice awakening method and device, computer equipment and a storage medium. The method comprises the following steps: detecting a trigger signal in a standby state, recording first time, when the trigger signal meets a preset condition, converting the standby state into a monitoring state, and collecting a voice monitoring signal in the monitoring state, inputting the voice monitoring signal into a voice category detection model to obtain a detection result, recording second time, determining a target time period according to the first time and the second time when the detection result is the defect wake-up word category, and converting the monitoring state into a running state according to the defect wake-up word category when the target time period is within apreset time period. By adopting the method, the wake-up success rate can be improved on the low-power-consumption wake-up device using the front sensor.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a voice wake-up method, device, computer equipment and storage medium. Background technique [0002] With the development of voice recognition technology, the device to be woken up can be woken up by using keyword voice. Usually, in the device to be woken up, high-power microphones (MIC), analog-to-digital converters (ADC), and algorithm processors (MCU or DSP) are turned off to achieve the purpose of low-power standby of the device to be woken up. However, in this case, when the device to be woken up is first awakened, due to the presence of the front sensor, there will be a certain delay when the front sensor is triggered, and after the front sensor is triggered, the microphone (MIC) will be turned on , the analog-to-digital converter (ADC), and the algorithm processor (MCU or DSP), etc., will also have a certain delay, resulting in the phenomenon of voice signal l...

AI Technical Summary

Problems solved by technology

However, in this case, when the device to be woken up is first awakened, due to the existence of the front sensor, there will be a certain delay when the front sensor is triggered, and after the front sensor is triggered, the microphone (MIC) is turned on , the analog-to-digital converter (ADC), and the algorithm processor (MCU or DSP) will also have a certain delay, resulting in the loss of voice signals, resulting in a lower wake-up success rate of the device to be woken up in the standby state

Images