Unlock instant, AI-driven research and patent intelligence for your innovation.

Baby cry intention recognition method and device based on hybrid neural network

A hybrid neural network and neural network technology, applied in the field of infant crying intention recognition, can solve the problem of low recognition accuracy and achieve the effect of improving accuracy

Active Publication Date: 2021-02-19
谭昊玥
View PDF10 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to solve the problem of low recognition accuracy in existing algorithms for automatically identifying the cause of infant crying, and proposes a hybrid neural network-based method and device for identifying the intention of infant crying

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
  • Baby cry intention recognition method and device based on hybrid neural network
  • Baby cry intention recognition method and device based on hybrid neural network
  • Baby cry intention recognition method and device based on hybrid neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0036] The baby cry intention recognition method based on hybrid neural network described in the embodiment of the present invention, such as figure 1 shown, including the following steps:

[0037] Step S1, obtaining a data set containing audio data of a baby crying and its corresponding intent probability;

[0038] Specifically, the data set can be obtained through the baby cry database, which can be collected from various types of baby cry data on YouTube and other websites through the study of Dunstan's baby language theory, after preprocessing, etc. Steps to build the baby cry database.

[0039] The data set includes audio data of various types of baby crying sounds and their corresponding intention probabilities. The corresponding intentions may include: hunger, sleepiness, hiccup, pain, discomfort, etc.

[0040] Step S2, establishing an intention recognition model based on CNN+DNN neural network;

[0041] In this example, if figure 2 As shown, the front section of t...

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 relates to the technical field of voice recognition, aims to solve the problem of low recognition accuracy of an existing algorithm for automatically recognizing baby cry reasons, and provides a baby cry intention recognition method and device based on a hybrid neural network. According to the main technical conception, the method comprises the steps of: acquiring audio data containing baby cry and a data set of intention probability corresponding to the audio data; establishing an intention recognition model based on a CNN + DNN neural network; training the intention recognitionmodel based on the CNN + DNN neural network according to the data set; and performing intention recognition on the audio data of a baby cry to be recognized according to the trained intention recognition model based on the CNN + DNN neural network. According to the invention, the accuracy of baby cry intention recognition is improved.

Description

technical field [0001] The present invention relates to the technical field of speech recognition, in particular to a method and device for recognizing the intention of a baby's cry based on a hybrid neural network. Background technique [0002] With the development of artificial intelligence and voice technology in recent years, it has become possible to recognize the intention of babies crying. Through the algorithm that automatically recognizes the reasons for babies crying, it can make it easier for parents to understand the specific meaning of babies crying, so as to help babies Healthier growth. [0003] Most of the algorithms in the prior art for automatically identifying the cause of a baby's crying are realized by using MFCC characteristic parameters. For example, the identification algorithm of infant crying cause based on codebook, the identification algorithm of infant crying cause based on neural network, the deep learning algorithm of identifying the cause of ...

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): G10L25/24G10L25/30G10L25/51G06N3/08G06N3/04
CPCG10L25/51G10L25/30G06N3/08G10L25/24G06N3/045
Inventor 谭昊玥
Owner 谭昊玥