A Baby Crying Detection Method Based on Interval Difference Feature

A detection method, infant technology, applied in speech analysis, instruments, etc., can solve problems such as external audio interference, achieve the effect of less false detection and missed detection, fast overall speed, and accurate detection results

Active Publication Date: 2018-11-30
ANHUI TSINGLINK INFORMATION TECH
View PDF10 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of technology can achieve the detection effect in an ideal environment. However, there are many shortcomings, such as serious false detection. This type of technology only passively accepts external audio. , TV audio, adults coughing, etc. Similarly, this type of technology will have missed detection

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
  • A Baby Crying Detection Method Based on Interval Difference Feature
  • A Baby Crying Detection Method Based on Interval Difference Feature
  • A Baby Crying Detection Method Based on Interval Difference Feature

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0050] A method for detecting infant crying based on interval difference features, comprising a training step and a detection step, specifically as follows:

[0051] The function of the training step is to obtain a baby crying audio classifier, which mainly uses the audio waveform data as a learning sample, adaptively selects the optimal features based on the adaboost learning algorithm for training, and obtains the corresponding classifier learning files, such as figure 1 shown, including the following steps:

[0052] T1. Collect positive samples for training, mainly audio waveform data of various crying babies, including audio waveform data of crying babies of different age groups and situations. The duration of each waveform data is 15 seconds, such as image 3 shown.

[0053] T2. Collect training negative samples, mainly all possible audi...

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 baby crying detection method based on interval difference features. The method comprises steps: audio waveform data are collected; audio energy features are acquired; whether the audio belongs to suspicious baby crying audio is judged, and if yes, background interference audio is removed; candidate baby crying audio position intervals are detected; statistical features for any one audio position interval are acquired; and whether the audio is baby crying audio is judged, and if yes, an alarming signal is given. A logic structure which combines coarse detection and fine detection is adopted, and the overall system speed is faster; adaptive machine vision learning algorithm is adopted to acquire the optimal training sample features, the detection result is more accurate, and false detection and missing detection are less; and influences from external environment audio are fewer.

Description

technical field [0001] The invention relates to the technical field of audio processing, in particular to a baby crying detection method based on interval difference features. Background technique [0002] Crying is the instinctive reaction of babies, especially for babies less than two years old, because they do not yet have the ability to express language, crying is the most important way for them to express their emotions and respond to external stimuli. People need to be looked after in time. However, in the real environment, it is impossible for the caregiver to take care of the baby all the time, especially when the baby is asleep, he will often engage in other tasks, such as doing housework, watching TV, etc. If the baby is crying at this time , caregivers, especially the elderly, are often deaf and unable to take care of them in time, which may cause some unexpected injuries to the baby and bring sadness to the whole family. [0003] At present, there are some tech...

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 Patents(China)
IPC IPC(8): G10L25/78
Inventor 张卡尼秀明何佳赵章伦
Owner ANHUI TSINGLINK INFORMATION 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