Sensitivity adjustability-based speech emotion recognition method and system

A speech emotion recognition and emotion recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of weak signal, incomplete emotion recognition by speech model, strong noise, etc., and achieve the effect of improving the recognition rate.

Active Publication Date: 2018-09-21
NANJING NORMAL UNIVERSITY
View PDF4 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Speech information itself contains rich emotional information, but not all the emotional information, and the audio signal itself has some inherent defects, such as weak signal, strong noise, etc. It is not comprehensive to recognize emotion from a single speech model

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
  • Sensitivity adjustability-based speech emotion recognition method and system
  • Sensitivity adjustability-based speech emotion recognition method and system
  • Sensitivity adjustability-based speech emotion recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The present invention will be described in further detail below in conjunction with the accompanying drawings and implementation examples.

[0055]The overall block diagram of a speech emotion recognition method and system based on adjustable sensitivity disclosed by the present invention is as follows: figure 1 As shown, the method and system extract the speech feature vector and the text feature vector respectively from the speech and the speech information and speech text information obtained by the speech recognition software; The probability of each speech emotion, using the emotion perception sensitivity adjustment module ERAdjust to set the judgment weight of each emotion, and the final recognized emotion is obtained by the decision fusion layer. The above-mentioned method disclosed by the present invention sets up the steps as follows:

[0056] (1) Speech and text dataset collection for model training

[0057] The four types of emotions are respectively happy,...

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 sensitivity adjustability-based speech emotion recognition method and system. According to the method and system, the input speech signals of a user are received; voice recognition software is utilized to perform text recognition on the speech signals, a speech signal feature vector and a text feature vector are established; the speech signal feature vector and the text feature vector are respectively inputted into a speech emotion recognition model and a text emotion recognition model for performing recognition, so that the class probabilities of the speech corresponding to four emotions are determined; a user can adjust the weighting values of judgment on the four emotions; and a decision-making layer fuses four emotion perception sensitivity-weighted emotion probabilities so as to obtain a final recognition result, and emotion sensitivity adjustable emotion recognition is realized. With the method and system of the invention adopted, new solutions and application methods can be brought for human-computer interaction, emotion management and emotion calculation.

Description

technical field [0001] The invention belongs to the field of voice recognition, in particular to a voice emotion recognition method and system based on adjustable sensitivity. Background technique [0002] Emotion is a common expression of human means of communication and plays an important role in human-computer interaction. Speech, as the most direct means of communication for human beings, can convey rich emotional information, and has been successfully used in automatic recognition of emotions. Although speech emotion recognition has achieved applicability, different emotions have different importance to human communication and response. Human beings have different sensitivities when recognizing different emotional changes, such as special emotions such as anger and sadness in the tone of voice. Sensitive perception of presence is important for effective communication. The current speech emotion recognition system generally adopts the decision-making method with the sm...

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): G10L15/02G10L15/14G10L15/16G10L15/26G10L25/21G10L25/30G10L25/63
CPCG10L15/02G10L15/14G10L15/16G10L15/26G10L25/21G10L25/30G10L25/63
Inventor 王蔚冯亚琴
Owner NANJING NORMAL UNIVERSITY
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