An offline voice control method, system and storage medium based on d2d technology

A voice-controlled, offline technology, applied in voice analysis, voice recognition, instruments, etc., can solve problems such as gateway crashes and inability to communicate

Active Publication Date: 2022-07-26
广东睿住智能科技有限公司
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the embodiments of the present invention is to provide an offline voice control method, system and storage medium based on D2D technology, which can solve the problem that communication cannot be performed after the traditional network gateway crashes, thereby realizing offline voice control equipment

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
  • An offline voice control method, system and storage medium based on d2d technology
  • An offline voice control method, system and storage medium based on d2d technology
  • An offline voice control method, system and storage medium based on d2d technology

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0044] see Figure 1-3 .

[0045] like figure 1 As shown, this embodiment provides an offline voice control method based on D2D technology, which at least includes the following steps:

[0046] S101. After pre-collecting the voice command words input by the user, perform front-end processing and acoustic feature extraction processing successively through a voice recognition algorithm to obtain corresponding acoustic feature data.

[0047] S102. Decode the acoustic feature data, construct a WFST search space model, and generate a list of voice command words.

[0048] Specifically, for steps S101 and S102, the user pre-enters the relevant voice command words through the voice acquisition system of the device, converts the voice analog signal into a digital signal through the voice signal analog-to-digital conversion circuit, and then inputs it into the special DSP chip for voice processing, The DSP chip uses the voice recognition algorithm software to perform front-end proces...

no. 2 example

[0079] like Figure 4 As shown, this embodiment provides an offline voice control system based on D2D technology, including:

[0080] The preprocessing module 100 is configured to perform front-end processing and acoustic feature extraction processing successively through a voice recognition algorithm after pre-collecting the voice command words input by the user to obtain corresponding acoustic feature data.

[0081] A WFST module 200 is constructed to decode the acoustic feature data, construct a WFST search space model, and generate a list of voice command words.

[0082] Specifically, for the preprocessing module 100 and the building WFST module 200, the user pre-enters the relevant voice command words through the voice acquisition system of the device, converts the voice analog signal into a digital signal through the voice signal analog-to-digital conversion circuit, and then inputs it to the voice processing dedicated In the DSP chip of the DSP chip, the DSP chip uses ...

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 invention discloses an off-line voice control method, system and storage medium based on D2D technology. The method includes: after pre-collecting the voice command words input by a user, performing front-end processing and acoustic feature extraction processing through a voice recognition algorithm, and obtaining After the acoustic feature data is decoded, a WFST search space model is constructed to generate a list of voice command words; after collecting the user's voice input signal in real time, the WFST search space model is used to find the optimal path with the highest matching probability, and the optimal recognition result is obtained. The voice command word list is compared, and after the comparison result is obtained, the voice control command is matched, and the voice control command is transmitted to the device equipped with the D2D module through D2D technology to complete the communication and control of the device. The invention can solve the problem that communication cannot be performed after the traditional network gateway collapses, and can connect to the wireless communication network by means of the D2D technology in the blind area of ​​network communication coverage by means of user terminals in the wireless network coverage area.

Description

technical field [0001] The present invention relates to the technical field of smart home, in particular to an offline voice control method, system and storage medium based on D2D technology. Background technique [0002] In recent years, a large number of intelligent terminal devices have shown an ever-increasing situation, and emerging communication services that meet the specific needs of users are also on the rise. Therefore, how to effectively increase network capacity, improve wireless spectrum utilization, and improve end-user experience under different communication modes has become an urgent task. The key technologies proposed by 5G will be promising in solving the above problems, including wireless technology and network technology. In terms of wireless technologies, technologies such as Device-to-Device (D2D), large-scale antenna arrays, full-spectrum access, ultra-dense networking, and new multiple access have become the focus of attention in the industry. [0...

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): G10L15/02G10L15/18G10L15/22G10L15/28
CPCG10L15/02G10L15/22G10L15/18G10L15/28G10L2015/223
Inventor 陈品良李强魏会杰
Owner 广东睿住智能科技有限公司
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