Method and apparatus for voice recognition, electronic device, and computer readable storage medium

Abstract

The embodiment of the invention provides a method and apparatus for voice recognition, an electronic device, and a computer readable storage medium. The method comprises: on the basis of sounds in a current environment, whether the current environment is in a mute state is determined; if not, whether the sounds in the current environment belong to preset noises is determined by a first model and / or a second model; and if not, a voice model is triggered to carry out keyword detection. Therefore, the probability of false triggering is reduced and the processing pressures of the collecting deviceand the keyword detecting device are reduced, so that the user experience is improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of speech recognition, and specifically, embodiments of the present invention relate to a speech recognition method, device, electronic equipment, and computer-readable storage medium. Background technique [0002] With the development of information technology, speech recognition technology develops accordingly. Using speech recognition technology to identify whether the sound in the current environment can trigger the execution of operations, for example, using speech recognition technology to recognize that the voice uttered by the user contains keywords that trigger the opening of the terminal device. , when the keyword that triggers the terminal device to be turned on is recognized, the terminal device is controlled to start up. Therefore, how to execute the trigger operation based on voice recognition becomes a key issue. [0003] In the prior art, a voice recognition method for v...

AI Technical Summary

Problems solved by technology

[0004] However, in the process of carrying out the invention, the inventor found that as long as the surrounding environment is not in the silent state, the keyword detection is triggered, because there may be some noises in the surrounding environment, such as people screaming, dog barking and other sounds, may be falsely triggered to collect sounds in the surrounding environment, and trigger keyword detection with the syllables in the voice model, resulting in a higher probability of false triggers; moreover, after false triggering, it is necessary to collect the sounds of the surrounding environment in real time Keyword detection leads to high processing pressure on the collection device and keyword detection device, and after keyword detection is falsely triggered, other voice commands may be falsely triggered to execute, resulting in poor user experience

Images