Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Speech recognition method and device, equipment and medium

A speech recognition and speech recognition model technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of speech recognition process influence, affect speech recognition success rate, and unsatisfactory noise reduction effect, so as to improve the speech recognition success rate , Improve the effect of voice quality

Pending Publication Date: 2021-11-30
QINGDAO HAIER WASHING MASCH CO LTD +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the development of voice recognition technology, many smart devices can be controlled by voice without manual operation by the user, which brings great convenience to people's life. However, when the smart device collects the user's voice control instructions, it may The noise from other devices or people around will be collected together, which will affect the subsequent speech recognition process
[0003] In the prior art, in order to improve the success rate of speech recognition, before the smart device performs speech recognition, it usually performs noise reduction processing on the received speech control instructions according to the pre-trained noise reduction model, and then performs noise reduction processing on the speech control commands after the noise reduction processing. Instructions for speech recognition, this method can only achieve noise reduction for specific environmental noises. When the environment where the smart device is located changes, the noise reduction effect will become unsatisfactory, thus affecting the success rate of speech recognition

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 and device, equipment and medium
  • Speech recognition method and device, equipment and medium
  • Speech recognition method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] figure 1 It is a flow chart of a speech recognition method in Embodiment 1 of the present invention. The technical solution of this embodiment is applicable to the situation where the volume of the main noise source is reduced before receiving a speech command. This method can be executed by a speech recognition device, which can It is realized by software and / or hardware, and can be integrated in various general-purpose computer devices, specifically including the following steps:

[0026] Step 110: Determine the main noise source according to the scene where the household electrical appliance receives the wake-up voice from the user.

[0027] Wherein, the main noise source refers to the noise source that has a greater impact on the user's voice command. Exemplarily, the main noise source may be a device with a relatively high operating noise among smart home appliances, such as a smart washing machine, a smart TV, and a smart cooking fume machine etc.

[0028] In th...

Embodiment 2

[0061] figure 2 It is a flowchart of a speech recognition method in Embodiment 2 of the present invention. This embodiment is further refined on the basis of the above embodiments, and provides specific steps for sending volume control instructions to the main noise source. Combine below figure 2 A speech recognition method provided in Embodiment 2 of the present invention is described, including the following steps:

[0062] Step 210: Determine the main noise source according to the scene where the household electrical appliance receives the wake-up voice from the user.

[0063] Step 220: Obtain the current time, and determine the usage frequency of at least one device included in the main noise source within the time period of the current time.

[0064] Wherein, the frequency of use of the device is the ratio of the number of times of use to the number of days in the set period of time in the set number of days. For example, the frequency of use within 30 days refers to ...

Embodiment 3

[0076] image 3 A schematic structural diagram of a speech recognition device provided by Embodiment 3 of the present invention, the speech recognition device includes: a main noise source determination module 310 , a volume control instruction sending module 320 and a speech recognition module 330 .

[0077] The main noise source determination module 310 is used to determine the main noise source according to the scene where the household electrical appliance receives the user's wake-up voice;

[0078] A volume control instruction sending module 320, configured to send a volume control instruction to the main noise source, and the volume control instruction is used to instruct the main noise source to reduce the volume;

[0079] The voice recognition module 330 is configured to receive a user's voice command, and perform voice recognition on the voice command through a voice recognition model.

[0080] According to the technical solution of the embodiment of the present invent...

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

The embodiment of the invention discloses a speech recognition method and device, equipment and a medium. The speech recognition method comprises the following steps: determining a main noise source according to a scene in which the household appliance receives a user wake-up voice; sending a volume control instruction to the main noise source, wherein the volume control instruction is used for indicating the main noise source to reduce the volume; and receiving a speech instruction of a user, and performing speech recognition on the speech instruction through the speech recognition model. According to the technical scheme, the volume of the main noise source is reduced before the speech instruction of the user is collected, and the speech recognition model is adopted for speech recognition so that the influence of an environmental noise on the speech instruction of the user is reduced, and a speech recognition success rate is improved.

Description

technical field [0001] The embodiments of the present invention relate to the field of smart home, and in particular, to a voice recognition method, device, equipment and medium. Background technique [0002] With the development of voice recognition technology, many smart devices can be controlled by voice without manual operation by the user, which brings great convenience to people's life. However, when the smart device collects the user's voice control instructions, it may The noise from other devices or people around will be collected together, which will affect the subsequent speech recognition process. [0003] In the prior art, in order to improve the success rate of speech recognition, before the smart device performs speech recognition, it usually performs noise reduction processing on the received speech control commands according to the pre-trained noise reduction model, and then performs noise reduction processing on the speech control commands after the noise r...

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
IPC IPC(8): G10L15/22G10L15/20G10L15/06
CPCG10L15/22G10L15/20G10L15/06G10L15/063G10L2015/223
Inventor 吕佩师丁晓鹏许升
Owner QINGDAO HAIER WASHING MASCH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com