A smart device wake-up method and device based on artificial intelligence

Abstract

The embodiment of the present application discloses a method for waking up a smart device based on artificial intelligence. For the acquired audio to be identified, it is determined whether the wake-up condition of the smart device is satisfied by analyzing the audio feature data of the audio frame. If it is determined that the wake-up condition is met according to the target audio frame, a plurality of audio feature data of the audio frame sequence is obtained, and the audio frame sequence includes the target audio frame and the adjacent audio frames of the target audio frame in the audio to be recognized, and is determined by the target acoustic model. The posterior probabilities corresponding to the plurality of audio feature data respectively, and the posterior probability of each audio frame may be used to identify the probability of indicating wake-up according to the audio feature data. The target acoustic model needs to determine whether to wake up as a whole according to all the posterior probabilities determined by the audio frame sequence. When the audio frame sequence does not carry the audio information corresponding to the complete wake-up word, the target acoustic model can effectively prevent wake-up and reduce false wake-up. The frequency of occurrence improves the user experience.

Description

technical field [0001] The present application relates to the field of data processing, and in particular, to an artificial intelligence-based smart device wake-up method and device. Background technique [0002] At present, smart devices are becoming more and more popular, and are widely used in people's work and life. [0003] Some smart devices are in a dormant state when not providing services. When users need to use such smart devices, they can wake up the smart devices by speaking a wake-up word by voice. [0004] However, the current related technology has a high false wake-up rate, that is, some noises or non-wake-up words are mistakenly recognized as wake-up words, and the smart device is incorrectly woken up, causing the smart device to suddenly start when the user does not need it. , causing adverse effects on users. SUMMARY OF THE INVENTION [0005] In order to solve the above technical problems, the present application provides an artificial intelligence-bas...

AI Technical Summary

Problems solved by technology

[0004] However, the current related technologies have a high false wake-up rate, that is, some noise or non-wake-up word voices are misidentified as wake-up word voices, and wrongly wake up the smart device, causing the smart device to suddenly start when the user does not need it. , causing adverse effects on users

Images