Awakening method, device and terminal

Abstract

The invention discloses an awakening method and device and a terminal, which are applied to the technical field of artificial intelligence voice. In the scheme provided by the invention, the voice input by a user to equipment with an awakening function is monitored, and under the condition that the voice is monitored to contain an awakening word or under the condition that an awakening verification result is determined to possibly cause false awakening, a sensor on the equipment is started to detect whether someone exists around the equipment or not so as to assist in determining whether the current voice awakening is successful awakening or false awakening, false awakening is reduced, and the awakening accuracy is improved. According to the scheme provided by the invention, the problem that in the prior art, the wakeup rate is reduced when the wakeup threshold is improved due to reduction of the false wakeup rate is solved, and the problems that the cost of manpower, material resources, time and the like is increased and a new scene cannot be effectively and quickly adapted due to addition of a scheme of new model training to adapt to a new environment are also solved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a wake-up method, device and terminal. Background technique [0002] In the current voice interaction technology, most of the voice interaction systems need to be woken up before starting the interaction, so that the voice interaction function can be further performed. During the wake-up process, false wake-up is easy to occur. At present, there are two main solutions to solve or reduce false wake-ups: [0003] One is to increase the wake-up threshold through manual configuration to reduce false wake-ups in cluttered environments such as stores and exhibitions. The purpose is to reduce the false wake-up rate in some noisy environments. Although this type of technical solution has completed the avoidance of false wake-up, it is not a real solution to optimize false wake-up because the increase of the wake-up threshold also leads to a decrease in the wake-...

AI Technical Summary

Problems solved by technology

Although this type of technical solution has completed the avoidance of false wake-ups, it is not a real solution to optimize false wake-ups due to the increase in the wake-up threshold and the reduction of the wake-up rate.

[0004]The other is to reduce false wake-ups by unilaterally controlling the wake-up model, that is, let the wake-up model learn a variety of new scenarios, so that the wake-up model can adapt to Various new scenarios, thereby reducing the false wake-up rate, but the usual defect of this solution is that every time a new environment or scenario is encountered, new model training needs to be added, requiring a large amount of new training data, and these training Data collection, labeling, and model training will bring a lot of manpower, material resources, time and other costs, and cannot effectively and quickly adapt to new scenarios

[0005]In summary, the first scheme to increase the wake-up threshold will reduce the wake-up rate while reducing the false wake-up rate, and the second scheme to increase the training of new models to adapt to the new environment The solution will lead to an increase in manpower, material resources, time and other costs, and cannot effectively and quickly adapt to new scenarios

Images