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

Dialect voice AI control method, device and terminal

A control method and voice technology, applied in voice analysis, voice recognition, voice input/output, etc., can solve the problems of pseudo-intelligence, inability to use, and difficulty in complete recording, and achieve the effects of intelligent humanization and reduced production costs

Inactive Publication Date: 2019-07-05
SHENZHEN SHANGKE DECORATION TECH CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there are more than 6,000 to 10,000 languages ​​in the world, and most of the dialects are languages ​​without written characters. It is difficult to completely record such languages.
The existing technology has the following defects: AI voice intelligence requires standard mandarin control, and if mandarin is not standard, it cannot be used, and it is easy to be defined as pseudo-intelligence
For some language recognition devices, large data from the network cloud voice library is required, and the network cannot be disconnected, otherwise it cannot be used

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
  • Dialect voice AI control method, device and terminal
  • Dialect voice AI control method, device and terminal
  • Dialect voice AI control method, device and terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Such as figure 1 As shown, the present invention is a dialect speech AI control method, and the described method is specifically:

[0040] S1. Obtain a wake-up word and a control command;

[0041] S2. Enter the language learning state according to the control instruction;

[0042] S3. Performing language replication through the voice information obtained multiple times;

[0043] S4. Analyze the copied language information and translate it with the mainstream language;

[0044] S5. Control the smart product according to the mutual translation entry.

[0045] Step S1. Acquire wake-up words and control instructions. There are three kinds of instructions for controlling the language brain:

[0046] The first method: wake-up words and control commands. This method is called One Shot. It is usually used on smart speakers, but it is the most convenient method for voice control, such as: Xiao Ke and turn on the light.

[0047] The second type: say control commands separate...

Embodiment 2

[0060] The process of withdrawing from studies is:

[0061] If the system plays "Please say the learning instruction of xxx for the xth time" and the user does not speak, after 30 seconds, the system will play "Learning timeout, system restart is taking effect", and the system will automatically exit the learning mode. Dialect commands that have been successfully learned will be retained, and the dialect can still be recognized.

Embodiment 3

[0063] System device technical parameters:

[0064] The system device is powered by a 5V USB port. Plug in the microphone and speaker. After power-on, the speaker will play "xxx is ready" in about 8 seconds.

[0065] There are three control modes: store mode, family mode, and kitchen mode. After the store mode acquires the copied voice information, the steady-state noise and dynamic noise are filtered. When the control mode is set to home mode, the ambient noise does not exceed 60 decibels, the recognition distance does not exceed 5 meters, and the speaking voice is higher than the surrounding noise, which can be effectively recognized.

[0066] When the control mode is set to store mode, the recognition distance does not exceed 1 meter, and the speaking voice is higher than the surrounding noise, which can be effectively recognized. It is best to keep your mouth facing the microphone, and do not bow your head or face in other directions.

[0067] Such as figure 2 As show...

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 relates to the field of intelligent voice control, in particular to a dialect voice AI control method, a dialect voice AI control device and a terminal. The dialect voice AI control method comprises the steps of obtaining a wake-up word and a control instruction; entering a language learning state according to the control instruction; carrying out language copying through the voice information obtained for multiple times; analyzing the copied language information and translating the language information with a mainstream language; and controlling the intelligent product accordingto the inter-translation entry. By means of the method, the dialect learning and the intelligent product control can be achieved in the non-networked state.

Description

technical field [0001] The invention relates to the field of intelligent voice control, in particular to a dialect voice AI control method, device and terminal. Background technique [0002] AI is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science. It attempts to understand the essence of intelligence and produce A new kind of intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robotics, language recognition, image recognition, natural language processing, and expert systems. [0003] The above-mentioned language recognition can convert language and voice into information that can be processed. At present, there are more than 6,000 to 10,000 languages ​​in the world, and most of the dialects have no written language, so it is difficult to make a comp...

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 Applications(China)
IPC IPC(8): G10L15/22G10L15/00G10L15/06G10L25/51G06F3/16
CPCG06F3/167G10L15/005G10L15/063G10L15/22G10L25/51G10L2015/223
Inventor 刘吉林
Owner SHENZHEN SHANGKE DECORATION TECH 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