A voice command recognition method, device and system

Abstract

The present invention discloses a voice instruction recognition method, device and system. The method includes: step 101, acquiring a first signal, the first signal is a user voice instruction superimposed with background noise; step 102, based on the first A signal identifies the identity of the user in the car; step 103, according to the correspondence between the identity in the car and the sound pickup device outside the car, determine the sound pickup device outside the car corresponding to the identity in the car of the user, from the outside of the car The sound pickup device acquires the second signal collected by it; Step 104, based on the second signal, process the first signal to obtain a user voice instruction for removing background noise; Step 105, based on the method for removing background noise The user's voice command is used for speech recognition and semantic recognition. Through the method of the present invention, the situation that the voice command cannot be recognized or the recognition error caused by the noise outside the vehicle when the window is opened is avoided, the recognition rate of the voice command is improved, and the user experience is improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of information processing, and in particular, to a voice command recognition method, device and system. Background technique [0002] In recent years, intelligence has gradually become the future development direction of automobiles. Voice control, as one of the manifestations of automobile intelligence, has received great attention. Through the voice control function, the user can avoid manual operation, and can control the car machine to perform specific operations only by using voice, such as turning on or off the air conditioner, setting navigation / modifying navigation, turning on music playback, etc., which greatly improves the user experience. . [0003] However, the current voice control function has insufficient recognition accuracy and is easily affected by environmental noise. For example, when the car window is opened, the presence of tire noise, wind noise, and environmenta...

AI Technical Summary

Problems solved by technology

[0003] However, the current voice control function has insufficient recognition accuracy and is easily affected by environmental noise. For example, when the car window is opened, the presence of tire noise, wind noise, and environmental noise will cause the voice command issued by the user to be submerged in the above noise. In this way, the voice command cannot be recognized or recognized incorrectly, which seriously affects the user's use of the voice control function.

[0004] There are some denoising methods in the prior art, but the acquired noise signal seriously deviates from the actual noise signal, resulting in insufficient denoising accuracy, and it is impossible to avoid the situation that the voice command cannot be recognized or the recognition is wrong, which affects the user experience

Images