Crying cause model building method and system and crying cause distinguishing method

A technology of reason model and establishment method, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of identifying babies and not being able to take care of babies correctly and in time, and achieve the effect of accurate identification

Inactive Publication Date: 2019-06-18
宝宝树(北京)信息技术有限公司
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for mothers who lack parenting experience, it is difficult to accurately identify the baby's needs from crying, and cannot take care of the baby's needs correctly and in a timely manner.

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
  • Crying cause model building method and system and crying cause distinguishing method
  • Crying cause model building method and system and crying cause distinguishing method
  • Crying cause model building method and system and crying cause distinguishing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] This embodiment provides a method for establishing a crying cause model, see figure 1 , which is a flow diagram of the method, by figure 1 Visible, this method comprises the following steps:

[0031] Step S102: Obtain crying data; the crying data includes at least one reason for crying.

[0032] Here, the cry data may be audio data, and its format may be MP3, WMA, WMV and so on. The category of cries may be human cries or cries of other animals. In this embodiment, the cry data is selected as the cry audio of a baby. Also, the cry data is not limited to one baby, but may be cry data of many babies.

[0033] Wherein, the acquired crying data has been classified, the reason of the crying has been judged, and the crying data is classified based on different reasons of crying. Here, data including at least one cause of crying is acquired.

[0034] In one of the possible implementation manners, the crying data may be acquired in the following manner:

[0035] First, g...

Embodiment 2

[0052] see figure 2 , is a schematic flowchart of another method for establishing a crying cause model provided by an embodiment of the present invention, wherein the method includes the following steps:

[0053] Step S202: Obtain crying data; the crying data includes at least one reason for crying.

[0054] Step S204: According to the crying data, the speech features corresponding to the data of each reason of crying are extracted.

[0055] In this embodiment, the speech features are Mel cepstral coefficient features and inverted Mel frequency cepstral coefficient features.

[0056] Step S206: using the speech features of all the reasons for crying to train a Gaussian mixture model to obtain a general background model. Here, the Gaussian mixture model is trained by using the speech features of all the causes of crying in the acquired crying data to obtain a general background model.

[0057] Step S208: using the speech features corresponding to each crying cause and the g...

Embodiment 3

[0061] The embodiment of the present invention provides a system for establishing a crying cause model, see image 3 , is the structural diagram of the system, by image 3 Visible, this system comprises the cry data acquisition module 31, voice feature extraction module 32 and cry cause model training module 33 connected successively, wherein, the function of each module is as follows:

[0062] A cry data acquisition module 31, configured to acquire cry data; the cry data is data that includes at least one reason for crying;

[0063] Voice feature extraction module 32, for extracting the voice feature corresponding to the data of every kind of cry reason according to this cry data;

[0064] The crying cause model training module 33 is configured to use the speech features corresponding to each crying cause to train a Gaussian mixture model to obtain a crying cause model corresponding to each crying cause.

[0065] The system for establishing the cause model of crying provide...

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 provides a crying cause model building method and system and a crying cause distinguishing method, and relates to the technical field of speech recognition. The crying cause model building method comprises acquiring crying data which contains data of at least one crying cause; extracting speech features corresponding to the data of each crying cause according to the crying data; training a Gaussian mixture model separately with the speech features of each crying cause to obtain crying cause models of the crying causes. The crying cause model building method and system and the crying cause distinguishing method provided by the embodiment allow crying causes to be distinguished more accurately by extracting crying features and modeling for the different crying causes.

Description

technical field [0001] The invention relates to the technical field of speech recognition, in particular to a method and system for establishing a crying cause model and a method for identifying the cause of crying. Background technique [0002] Crying is a way for babies to communicate with the outside world before they can speak. Babies communicate their emotions and illness to the outside world through crying. Experienced mothers can discern the baby's needs from their cries. However, for mothers who lack parenting experience, it is difficult to accurately identify the baby's needs from crying, and cannot take care of the baby's needs correctly and in a timely manner. Contents of the invention [0003] In view of this, the object of the present invention is to provide a method for establishing a crying cause model, a system and a method for identifying the cause of crying. Identify the cause, and more accurately identify the cause of crying. [0004] In the first as...

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): G10L25/63G10L15/06
Inventor 詹宏勇卓鹏鹏
Owner 宝宝树(北京)信息技术有限公司
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