Multi-tone area speech recognition method and device, and storage medium

Abstract

The embodiment of the invention provides a multi-tone area speech recognition method and device, and a computer-readable storage medium. The multi-tone area speech recognition method comprises the steps: collecting speech in a speech acquisition environment using a microphone module, wherein a target tone area is set for each microphone in the microphone module in advance, the target tone area being one of a plurality of independent tone areas in the speech acquisition environment set in advance; Judging whether the speech is from a target sound region; Suppressing speech from a sound region other than the target sound region; the suppressed speech is recognized. As the embodiment of the invention use a microphone module to isolate different sound regions, the voice use by all the staff inthe voice acquisition environment is realized by isolating a plurality of sound regions, and the isolation degree of each sound region can reach 15-20dB, the ideal isolation effect is achieved.

Description

technical field [0001] The present invention relates to the field of information technology, in particular to a multi-sound region speech recognition method, device and computer-readable storage medium. Background technique [0002] The traditional speech recognition technical solutions all focus on serving a target user. For example, the traditional in-vehicle voice recognition technology solution is designed around the driver alone, and the angle of the front-end microphone is aimed at the main driving position. The traditional core vertical navigation, music, phone, etc. are also designed around the driver. Among them, the vertical category is a vertical field, specifically referring to a certain field. Developers can set specific fields according to user usage scenarios to make the recognition results more accurate. For example, if the vertical field is set to "music", then the name of the song, artist name or lyrics related to music will be recognized preferentially d...

AI Technical Summary

Problems solved by technology

[0003] The defect of the traditional voice recognition technology solution is that it only serves one target user, and it is impossible to use voice services for all employees in the voice collection environment.

Still taking in-vehicle voice recognition as an example, the traditional voice recognition technology solution only serves the driver alone, and cannot realize the voice service for all people in the car, which brings poor user experience to the passengers in the car

Images