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

Road rage emotion judgment method and device based on speech recognition

A speech recognition and road rage technology, applied in speech analysis, neural learning methods, character and pattern recognition, etc., can solve the problems of unable to update speech recognition system algorithm parameters in time, low accuracy of speech recognition results, and lack of "road rage" emotions Judgment method Cloud-edge collaborative architecture and other issues to achieve the effect of reducing computing pressure, increasing reliability, and improving accuracy

Pending Publication Date: 2022-03-08
ZHEJIANG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The existing technology lacks the emotion judgment method of "road rage" based on speech recognition and the corresponding cloud-side collaborative architecture, and cannot update the algorithm parameters in the speech recognition system in time, resulting in low accuracy of speech recognition results

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
  • Road rage emotion judgment method and device based on speech recognition
  • Road rage emotion judgment method and device based on speech recognition
  • Road rage emotion judgment method and device based on speech recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] Such as figure 1 As shown, in this embodiment, the flow of the "road rage" emotion judgment method based on speech recognition can be preset, and according to the driver's audio obtained in real time according to the preset speech recognition-based "road rage" emotion judgment method flow, And preprocessing is carried out to obtain the target audio used for algorithm model processing, and the "road rage" emotion judgment is carried out on the target audio to obtain the recognition result.

[0042] Specifically, the real-time acquisition of the driver's audio and preprocessing include:

[0043] Obtain the original audio of the driver in real time, and extract the audio code stream from the original audio;

[0044] Using a library function to decode the audio code stream to obtain target audio that can be used for algorithm model calculation, the library function includes librosa and wave in python.

[0045]The "road rage" emotion judgment method flow of the speech reco...

Embodiment 2

[0080] Such as figure 2 As shown, in this embodiment, the algorithm update method of the speech recognition-based "road rage" emotion judgment method can be applied to the vehicle-mounted terminal, and is aimed at the parameters in the algorithm model, and the present invention can be directly integrated on the vehicle-mounted terminal The method provides the function of updating the algorithm parameters of the "road rage" emotion judgment based on speech recognition, or runs in the vehicle terminal in the form of a software development kit (Software Development Kit, SDK).

[0081] The method for updating algorithm parameters based on speech recognition-based "road rage" emotion judgment specifically includes the following steps. According to different requirements, the order of the steps in the flowchart can be changed, and some of them can be omitted.

[0082] S1, analyzing the original audio obtained in real time to obtain the target audio.

[0083] In this embodiment, th...

example 3

[0103] Such as image 3 As shown, the third aspect of the present invention provides a "road rage" emotion judgment device based on speech recognition. The device includes a vehicle terminal and a cloud platform:

[0104] The vehicle terminal includes: a central processing unit, a data acquisition module, a storage module, a communication module, an edge computing module and a camera;

[0105] Described data collection module is used for collecting driver's voice, obtains original audio frequency;

[0106] The storage module stores the driver's voice data collected, the algorithm model parameters of the current recognition node and the "road rage" emotion recognition result data based on speech recognition;

[0107] The communication module is used to realize the communication between the vehicle terminal and the cloud platform;

[0108] The edge computing module is used to preprocess the collected original audio to obtain the target audio for algorithm model processing; th...

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 road rage emotion judgment method and device based on voice recognition. The method comprises the following steps: acquiring audio of a driver in real time; the vehicle-mounted edge end carries out road rage emotion judgment results based on voice recognition on the audio and stores recognition model parameters; comparing face road rage emotion judgment results acquired based on videos; when the two results are different, the audio, the calculation result and the current model parameters are uploaded to the cloud platform, the cloud platform trains an algorithm model based on the uploaded data and sends updated algorithm model parameters to the vehicle-mounted end, and the edge end completes updating of the road rage emotion judgment algorithm parameters based on voice recognition. According to the method, the calculation pressure of the edge end is reduced through the parameters and the cloud-edge cooperation mode in the cloud-edge cooperation updating algorithm model, and the accuracy of speech recognition road rage is improved along with the increase of the driving duration of the driver.

Description

technical field [0001] The invention relates to a "road rage" emotion judgment method and device based on speech recognition, belonging to the fields of artificial intelligence, embedded system technology, digital signal processing technology and detection technology. Background technique [0002] In the proportion of the total number of accidents and the proportion of casualties in accidents, human factors account for nearly 90%. There is a very significant correlation between a driver's emotional state while driving and subsequent driving behavior. About 60.72% of motor vehicle drivers in our country have the experience of "road rage". [0003] Therefore, it is necessary to effectively detect the "road rage" emotion, and combined with the scalability of the speech anger emotion judgment model, a "road rage" emotion judgment method based on speech recognition is designed. Road rage is aggressive or angry behavior by the driver of a car or other motor vehicle. Such behavi...

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): G10L25/63G06V40/16G06N3/08G06N3/04
CPCG10L25/63G06N3/08G06N3/045
Inventor 徐新民王文婧沈鑫怡王煜
Owner ZHEJIANG UNIV
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