Likelihood probability fuzzy entropy based voice emotion automatic identification method at tension state

A technology of likelihood probability and tension state, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of poor classification reliability and misjudgment, achieve good recognition performance, ensure accuracy, and reduce misjudgment rate Effect

Inactive Publication Date: 2016-06-29
YANCHENG INST OF TECH
View PDF2 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Human emotions are ambiguous and diverse. In speech emotion recognition, the traditional recognition method is to rigidly divide the emerging samples into

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
  • Likelihood probability fuzzy entropy based voice emotion automatic identification method at tension state
  • Likelihood probability fuzzy entropy based voice emotion automatic identification method at tension state
  • Likelihood probability fuzzy entropy based voice emotion automatic identification method at tension state

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Below in conjunction with accompanying drawing, the present invention will be further described, a kind of speech emotion automatic recognition method under the state of tension based on likelihood probability fuzzy entropy, comprises the steps:

[0039] (1) Establish a voice database, the voice database includes tension, joy and calm voice data.

[0040] In experimental psychology, the stimulation of visual perception and auditory perception through computer multimedia technology has emerged with the development of computer technology in recent years, and more experimental methods are used. Computer games can provide an interactive and highly appealing human-computer interaction environment through the visual and auditory stimulation of pictures and music, and can effectively induce the positive and negative emotions of the subjects. Especially when the games are successively victorious, the subjects are induced to feel joyful emotions due to their success and satisfac...

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 likelihood probability fuzzy entropy based voice emotion automatic identification method at a tension state, for automatically identifying a tension emotion in voice. Linguistic data of the tension emotion is acquired through an inducement method and the data is enabled to be closer to real emotion data such that quite good identification performance of the tension emotion can be obtained. Besides, by use of a determination rejectable voice emotion identification method, for an uncertain or unknown emotion sample, a classifier gives an identification result of determination rejection, i.e., the sample does not belong to any one type among practical voice emotion types needing detection, such that the identification accuracy can be guaranteed and the misjudgement rate is effectively reduced.

Description

technical field [0001] The invention relates to a speech recognition method, in particular to a method for automatic recognition of speech emotion in a tense state based on likelihood probability fuzzy entropy. Background technique [0002] In artificial intelligence, affective computing is considered to be a key way to endow computers with higher and comprehensive intelligence. In human-computer interaction, endowing computers with anthropomorphic emotional capabilities, enabling them to perceive the surrounding environment and atmosphere, adaptively provide the most comfortable interactive environment, and try to eliminate the barriers between humans and machines has become the goal of the next generation of computer development. . Speech emotion recognition technology uses the method of pattern recognition to extract the speaker's emotional state information from the speech signal, so that the computer can automatically recognize the speech emotion, which is an important...

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): G10L25/63G10L25/27G10L15/01G10L15/02G10L15/18
CPCG10L25/63G10L15/01G10L15/02G10L15/1807G10L25/27
Inventor 周锋孙冬生王如刚周六英
Owner YANCHENG INST 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