Sentiment analytical method based on mobile phone voices and sentiment analytical system based on mobile phone voices

A sentiment analysis and speech technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of unreal sentiment analysis results, unnatural speech collection, inconvenient use, etc., to achieve real results, timely analysis, and simple methods. Effect

Inactive Publication Date: 2013-05-08
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, it is rare to analyze the user's emotional state by using mobile phone voice at home and abroad. The voice collection in voice emotion analysis is unnatural, inconvenient to use, and the result of emotion analysis is not true.

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
  • Sentiment analytical method based on mobile phone voices and sentiment analytical system based on mobile phone voices
  • Sentiment analytical method based on mobile phone voices and sentiment analytical system based on mobile phone voices

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0034] Such as figure 1 Shown, a kind of sentiment analysis method based on mobile phone speech, this method comprises the following steps:

[0035] Step 1, start the monitoring program of user conversation, enter the voice capture state of mobile phone conversation, monitoring program is a background resident program, when the user talks, it starts the voice acquisition program;

[0036] Step 2, the voice collection program records the voice during the call, and saves it as an MP3 audio file to the machine;

[0037] Step 3, extract the voice emotion feature of MP3 audio file, form a voice emotion feature vector; Voice emotion feature comprises short-term zero-crossing rate, short-term energy, pitch frequency, formant, harmonic-to-noise ratio, MFCC parameter, first-order MFCC Parameters, second-order MFCC parameters, LPC cepstral coefficients, linear prediction coefficients, subband energies, and frequency center mean, standard deviation, maximum, and minimum;

[0038] Step ...

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

A sentiment analytical method based on mobile phone voices includes mobile phone call status detection, voice signal acquisition, voice sentiment characteristic extraction, voice sentiment classification, content recommendation and local short message box writing. A sentiment analytical system based on the mobile phone voices comprises a mobile phone call status detection module, a voice signal acquisition module, a voice sentiment characteristic extraction module, a voice sentiment classification module, a content recommendation module and a local short message box writing module. The sentiment analytical method based on the mobile phone voices and the sentiment analytical system based on the mobile phone voices have the advantages of being simple in method and system structure, true in sentiment analytical result, and the like.

Description

technical field [0001] The invention relates to a voice signal processing and pattern recognition technology, in particular to an emotion analysis method and system based on mobile phone voice. Background technique [0002] The emotional state reflects the state of mental health. At present, many people are facing psychological pressure, and more or less there will be some psychological and emotional problems, manifested as irritability, anxiety, depression, etc., which need to be guided in time. People who lack academic knowledge are generally difficult to detect, so it is very important to automatically monitor and remind with the help of information technology. Speech contains rich emotional information and is an important way for us to understand emotions. Therefore, speech analysis can realize the identification of human emotional states. The mobile phone is a tool that people often use. The voice during the call reflects the user's natural emotion. Therefore, by autom...

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): G10L15/02G10L25/63
Inventor 文贵华黄金龙江丽君
Owner SOUTH CHINA UNIV OF TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap