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

Animal sound emotion feature set sorting recognition method and system

A technology of emotional features and recognition methods, applied in speech analysis, instruments, etc., can solve the problems of lack of continuity and stability of feature sets, low accuracy of voice emotion recognition, and inability of developers to customize feature factors.

Active Publication Date: 2021-04-09
DALIAN NEUSOFT UNIV OF INFORMATION
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the existing technology, there are mainly four problems in the automatic recognition of animal voice emotion: one is that under natural conditions, the accuracy of existing voice emotion recognition is low; the other is that the feature set of existing voice emotion recognition lacks continuity and stability ; The third is that when the number of samples is small, the classification effect of the existing voice emotion recognition is not good; the fourth is that developers cannot customize the feature factors according to the characteristics of the task

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
  • Animal sound emotion feature set sorting recognition method and system
  • Animal sound emotion feature set sorting recognition method and system
  • Animal sound emotion feature set sorting recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0067] Such as figure 1 As shown, the present embodiment provides a method for sorting and identifying animal voice emotional feature sets, including:

[0068] 101. Obtain the acoustic features of animal sounds, and construct a feature set of animal sounds;

[0069] Specifically, the collected animal sounds are made into audio, and multiple feat...

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 an animal voice emotion feature set sorting identification method. The method comprises the following steps of obtaining an animal voice feature set through feature extraction, ensuring a classification effect by using a large number of samples, and customizing feature factors by developers according to task features; through feature sorting, preliminarily determining credibility of different features in the emotion recognition task; through abnormal feature weight compensation, realizing preliminary adjustment of a feature sequence; through deep learning model compensation, optimizing the feature sequence so that the feature set of sound emotion recognition has continuity and stability and sound emotion recognition precision is improved.

Description

technical field [0001] The present invention relates to the technical field of animal voice emotion recognition, in particular to a method and system for sorting and identifying animal voice emotion feature sets. Background technique [0002] Automatic emotion recognition based on animal sounds is of great significance for the study of animal species, population and quantity, and the analysis of ecological environment. Sound as a form of communication requires machines intelligent enough to recognize animal sounds and animal emotions. With the development of machine learning, neural network and deep learning theory, the accuracy of related tasks such as sound emotion classification is gradually improving, which provides great help for computers to understand the expression of sound. In the existing technology, there are mainly four problems in the automatic recognition of animal voice emotion: one is that under natural conditions, the accuracy of existing voice emotion reco...

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): G10L25/63G10L25/24G10L25/03G10L25/30
CPCG10L25/63G10L25/24G10L25/03G10L25/30
Inventor 贾宁郑纯军李帅叶剑锋郭耸关思雨崔新明王江浩
Owner DALIAN NEUSOFT UNIV OF INFORMATION
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