Speech recognition method, device, device and storage medium

A speech recognition and speech technology, applied in speech recognition, speech analysis, measuring devices, etc., can solve problems such as misidentification of vehicles and machines, and achieve the effect of maintaining effectiveness, improving user experience, and good user experience

Active Publication Date: 2021-10-08
APOLLO INTELLIGENT CONNECTIVITY (BEIJING) TECH CO LTD
View PDF16 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At this time, if the voice of the phone is recorded by the microphone of the car, it may cause many misidentifications of the car

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Speech recognition method, device, device and storage medium
  • Speech recognition method, device, device and storage medium
  • Speech recognition method, device, device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0061] Example 1: Using a digital signal processor (DSP, Digital Signal Processor) to eliminate audio signals at other locations. Specifically, it may include: receiving the first voice signal of the microphone in the wake-up voice position; receiving the second voice signals of the microphones in other positions; using DSP to eliminate each of the second voice signals from the first voice signal , to get the signal to be identified. For example, the DSP can subtract signals that wake up individual microphones outside of the speech location.

[0062] In an application scenario, the voice signal received by the driver's microphone includes the voice signal received by the co-pilot's microphone. If the voice signal received by the microphone of the co-pilot can be obtained, the voice signal received by the microphone of the co-pilot can be eliminated from the voice signal received by the microphone of the driver. In this way, the influence of other microphones on the signal re...

example 2

[0063] Example 2: Control the microphone at the wake-up voice position to receive sound, and prohibit the microphone at other positions to receive sound. Specifically, it may include: controlling the microphone at the other position to stop sound collection; and receiving a signal to be recognized from the microphone at the wake-up voice position.

[0064] According to the above method of the embodiment of the present invention, by first determining the wake-up voice position, audio signals at other positions can be suppressed, thereby maintaining the validity of the voice at the wake-up voice position, reducing the impact of noise signals at other positions on speech recognition, Reduce disturbance to wake-up voice location. Therefore, it is more conducive to obtaining accurate speech recognition results and improving user experience.

[0065] In an application example, a speech recognition system of a vehicle is taken as an example. like image 3 As shown, the interior of...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

Embodiments of the present invention provide a voice recognition method, device, equipment, and storage medium. Wherein, the voice recognition method may include: acquiring multiple wake-up voice signals from multiple locations; performing sound source localization on the multiple wake-up voice signals to determine the position of the wake-up voice; The audio signal of the position is suppressed to obtain the signal to be recognized; voice recognition is performed on the signal to be recognized. By first determining the wake-up voice position, audio signals at other positions can be suppressed, thereby maintaining the validity of the voice at the wake-up voice position, reducing the impact of noise signals at other positions on speech recognition, and reducing the interference to the wake-up voice position.

Description

technical field [0001] The present invention relates to the technical field of voice recognition, in particular to a voice recognition method, device, equipment and storage medium. Background technique [0002] The current in-vehicle voice recognition system usually only allows voice input by a person at a specific location in a quiet environment. However, in the vehicle environment, there are often scenes where there are many people talking in the vehicle. For example, someone is on the phone, and at the same time someone else wants to initiate an operation such as navigation by voice. At this time, if the voice of the phone is recorded by the microphone of the car, it may cause many misidentifications of the car. Contents of the invention [0003] Embodiments of the present invention provide a voice recognition method, device, device, and storage medium to solve one or more technical problems in the prior art. [0004] In a first aspect, an embodiment of the present i...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G10L15/22G10L21/02G10L21/0216G01S5/18
CPCG10L15/22G10L21/02G10L21/0216G01S5/18G10L2021/02166
Inventor 陈建哲张腾飞向伟
Owner APOLLO INTELLIGENT CONNECTIVITY (BEIJING) TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap