Voice wake-up method and device, apparatus and storage medium

Abstract

The embodiment of the invention discloses a voice wake-up method and device, an apparatus and a storage medium. The method comprises the following steps of acquiring the voice information in real time, and identifying an environment type corresponding to the voice information; determining a target wake-up model from a preset wake-up model group according to the environment type corresponding to the voice information, the wake-up model group comprising at least two wake-up models, and different wake-up models corresponding to different environment types; and inputting the voice information intothe target wake-up model to detect a wake-up word, and executing a device wake-up operation when it is determined that the wake-up word is detected. By means of the technical scheme, the higher wake-up rate and the lower false awakening rate can be considered at the same time in different scenes.

Description

technical field [0001] Embodiments of the present invention relate to information processing technologies, and in particular, to a voice wake-up method, device, equipment, and storage medium. Background technique [0002] With the popularity of smart electronic devices, many electronic devices have a voice wake-up function. [0003] At present, the voice wake-up method mainly simply uses a wake-up model based on a deep neural network to detect whether the voice contains a wake-up word. If the wake-up word is detected, the device is woken up, otherwise the device remains silent. This technical solution performs well in quiet scenes, with low false wake-up rate and high wake-up rate, but it is not so outstanding in some noisy scenes, prone to high false wake-up rate or low wake-up rate. These noise scenes mainly include stores with strong noise, offices where people are talking, rooms where TV or music is playing, etc. These scenes are very common in life, and they also pose ...

AI Technical Summary

Problems solved by technology

This technical solution performs well in quiet scenes, with low false wake-up rate and high wake-up rate, but it is not so outstanding in some noisy scenes, prone to high false wake-up rate or low wake-up rate

These noise scenes mainly include stores with strong noise, offices where people are talking, rooms where TV or music is playing, etc. These scenes are very common in life, and they also pose challenges to voice wake-up technology.

[0004] In addition, in order to pursue a lower false wakeup rate and a higher wakeup rate in the prior art, it is necessary to improve the adaptability of the neural network model in different scenarios, usually by changing the model structure and increasing the model size to improve The adaptability of the model to different scenarios, but due to the limited chip space, it is impossible to achieve both a high wake-up rate and a low false wake-up rate in different scenarios

Images