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

Chinese voice interaction non-inductive control system based on Raspberry Pi edge calculation and method thereof

An edge computing and voice interaction technology, applied in the computer field, can solve the problems of large model size, low recognition accuracy, poor robustness, etc., and achieve the effect of small model size

Pending Publication Date: 2020-10-27
ENG UNIV OF THE CHINESE PEOPLES ARMED POLICE FORCE
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0013] In view of the deficiencies in the existing technology, the purpose of the present invention is to provide a Chinese voice interaction non-sensing control system and method based on Raspberry Pi edge computing, to realize the function of Chinese voice recognition interaction in harsh environments, and to solve the problem of voice interaction under harsh conditions. Poor robustness of recognition and speech synthesis technology, large model size, and low recognition accuracy

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
  • Chinese voice interaction non-inductive control system based on Raspberry Pi edge calculation and method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be described in further detail below in conjunction with specific examples, but not as a limitation of the present invention.

[0038] The Chinese voice interactive non-inductive control system based on Raspberry Pi edge computing of the present invention includes an edge terminal, a mobile terminal, an external control module and an edge computing detection and scheduling module; To elaborate:

[0039] Such as figure 1 As shown, the hardware system uses the Raspberry Pi as the mobile control terminal and the Internet of Things interface device, including the voice device module and the speech synthesis module, which has the advantage of being common to other Internet of Things modules on the market. The external control module adopts the I2C bus communication method , connected with drones and smart home interfaces; the edge end uses an X86 edge server to recognize speech through the end-to-end deep neural network MASR, and performs speech s...

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 Chinese voice interaction non-inductive control system based on Raspberry Pi edge calculation and a method thereof, and the system comprises an edge end, a mobile end, an external control module, and an edge calculation detection and scheduling module. According to the invention, the sizes of a speech recognition model and a speech synthesis model are small; the edge calculation and offline work can be realized, the equipment is directly deployed in mobile terminal equipment without depending on a network, the functions of voice synthesis and voice recognition can berealized under an offline condition, the problems of voice recognition and interaction functions under severe conditions such as unsmooth network or attack are solved, and the function of Chinese voice recognition interaction under a severe environment is realized.

Description

technical field [0001] The invention belongs to the field of computer technology, and relates to speech recognition technology, in particular to a Chinese speech interaction senseless control system and method based on raspberry pie edge computing. Background technique [0002] Speech recognition is to convert a piece of speech signal into corresponding text information. The system mainly includes four parts: feature extraction, acoustic model, language model, dictionary and decoding. In order to extract features more effectively, it often needs to be collected. The sound signal is preprocessed by filtering, framing, etc., and the signal to be analyzed is extracted from the original signal; after that, the feature extraction work converts the sound signal from the time domain to the frequency domain to provide a suitable feature vector for the acoustic model; In the model, the score of each feature vector on the acoustic feature is calculated according to the acoustic charac...

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): G10L15/22G06N3/04G06N3/08G10L13/02G10L15/06G10L15/16G10L15/18G10L15/30G10L25/18G10L25/30
CPCG10L15/22G10L13/02G10L15/16G10L15/18G10L15/063G10L15/30G10L25/18G10L25/30G06N3/08G06N3/045
Inventor 柏财通崔翛龙李爱
Owner ENG UNIV OF THE CHINESE PEOPLES ARMED POLICE FORCE
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