Supercharge Your Innovation With Domain-Expert AI Agents!

A self-learning voice control method, system and storage medium

A voice control, self-learning technology, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as inhumanity, labor-intensive, time-consuming, etc., to improve user experience and solve the effect of low flexibility

Active Publication Date: 2022-07-26
广东睿住智能科技有限公司
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in the process of research and practice of the prior art, the inventor of the present invention found that the offline speech recognition system currently on the market requires the user to formulate fixed instruction words first, and after the manufacturer passes frequent instruction words training, the speech Computing on the MCU processor to realize the basic recognition function is not only time-consuming and manpower-consuming, but also the instruction word training process is cumbersome and not humane enough

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
  • A self-learning voice control method, system and storage medium
  • A self-learning voice control method, system and storage medium
  • A self-learning voice control method, system and storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0044] see Figure 1-3 .

[0045] like figure 1 As shown, this embodiment provides a self-learning voice control method, which at least includes the following steps:

[0046] S101. After the user wakes up the device through the voice wake-up word, collect the user's voice input signal in real time, go through front-end processing, acoustic feature extraction processing and decoding processing successively, and filter the optimal path with the highest matching probability by constructing a WFST search space model to obtain the best recognition result.

[0047] Specifically, for step S101, as figure 2As shown, when the user speaks the voice wake-up word of the device and wakes up the voice device, the user's voice signal is collected in real time. The voice MCU is used for analysis and translation into command words, which are stored in the memory of the MCU for marking. When the voice acquisition system of the device collects the user's voice command words, the analog-to-d...

no. 2 example

[0082] like Figure 4 As shown, this embodiment provides a self-learning voice control system, including:

[0083] The voice recognition module 100 is used to collect the user's voice input signal in real time after the user wakes up the device through the voice wake-up word, and successively goes through front-end processing, acoustic feature extraction processing and decoding processing, and filters the ones with the highest matching probability by constructing a WFST search space model. The optimal path to obtain the optimal recognition result.

[0084] Specifically, for the voice recognition module 100, when the user speaks the voice wake-up word of the device and wakes up the voice device, it starts to collect the voice signal of the user in real time. The voice MCU is used for analysis and translation into command words, which are stored in the memory of the MCU for marking. When the voice acquisition system of the device collects the user's voice command words, the ana...

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 a self-learning voice control method, system and storage medium. The method comprises: collecting a user's voice input signal in real time; The optimal path with the highest matching probability is screened, and the voice command word in the optimal recognition result is obtained and matched with the voice command word list. If the match is successful, the corresponding voice control command is output; if the match is unsuccessful, the voice command word is processed. mark and upload it to the cloud backend; when the cloud backend detects that there are voice command words that exceed the preset number of marking times, it automatically downloads the voice command words to the DSP voice processing chip to complete the self-learning of the voice command words; after receiving the update command, Associate the newly added voice command word with the corresponding scene linkage mode. The present invention can deeply learn the user's daily voice command habits so as to update the voice command words and improve the user's voice control experience.

Description

technical field [0001] The invention relates to the technical field of smart home, in particular to a self-learning voice control method, system and storage medium. Background technique [0002] With the development of speech recognition technology, more and more devices have been embedded with speech recognition interaction technology. Users can control the corresponding lighting, curtains, air conditioners and other household devices online through speech to realize distributed control of speech. The speech recognition technologies on the market today are divided into online speech and offline speech. [0003] However, in the process of researching and practicing the prior art, the inventor of the present invention found that the offline speech recognition system currently on the market requires the user to formulate fixed command words first, and after the manufacturer passes frequent command word training, Performing operations on the MCU processor to realize the basic ...

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): G10L15/02G10L15/18G10L15/22G10L15/30G10L25/87G10L15/06
CPCG10L15/22G10L15/02G10L15/18G10L15/30G10L25/87G10L2015/223G10L2015/0635
Inventor 陈品良李强魏会杰
Owner 广东睿住智能科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com