Real time infant audio series behavior detecting method in domestic environment

A technology for home environment and detection methods, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of misrecognition, poor application effect, low recognition rate, etc., so as to reduce the misrecognition rate, reduce the impact, and increase the recognition rate. rate effect

Inactive Publication Date: 2018-03-16
深圳声联网科技有限公司
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For research in this area, some technologies at home and abroad are directly judged by sound frequency, without applying pattern recognition technology, so the recognition rate will be relatively low, and there is a large part of misrecognition, and the application effect is not very good

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
  • Real time infant audio series behavior detecting method in domestic environment
  • Real time infant audio series behavior detecting method in domestic environment
  • Real time infant audio series behavior detecting method in domestic environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The technical solutions of the present invention will be further elaborated below in conjunction with the accompanying drawings and embodiments.

[0035] Baby audio behavior detection plays a vital role in baby care and is of great help to children's healthy growth. However, at present, most of the researches in this area at home and abroad are aimed at a certain behavior, and the application is too single, or the detection method is not smart enough, which makes it difficult to obtain satisfactory recognition results. In view of this situation, the present invention proposes a real-time baby audio series behavior detection method in a home environment based on vector quantization technology. First, extract the frame speech features related to the baby's behavior for the training speech; then, train the speech model for each behavior; finally, when classifying the speech to be recognized in the actual environment, use the trained model to judge the category of each fram...

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 proposes a real time infant audio series behavior detecting method in a domestic environment. First, a corpus is established and audio data and background sound of multiple infant behaviors are collected in different channels, wherein the background sound includes infant other sound, adult sound of voices and different sound in the domestic environment. Voice characteristics relatedto infant behaviors, including tone-related characteristics, Mel-frequency cepstral coefficients and short term energy parameters, are extracted. Model parameters of each sound are obtained through training by utilizing a technical method of vector quantization. Finally, infant audio series behavior detection in the real time environment is implemented through segment based acceptation-rejection strategy in the domestic environment. Experiment results show that the infant cry detection and recognition rate in the domestic environment can reach 89% and the laughter detection and recognition rate can reach 85%.

Description

【Technical field】 [0001] The invention relates to a voice recognition technology, in particular to a real-time baby audio series behavior detection method in a home environment, which belongs to the field of voice signal processing. 【Background technique】 [0002] When a newborn baby cannot speak, a series of babbling sounds such as crying and laughing are the only way to communicate with the outside world, which can convey needs and discomfort, thereby attracting the attention of parents or babysitters to satisfy them. needs or relief of discomfort. The various voices of babies also contain various information about the body and physiology, such as health status, personality, gender, emotions and so on. [0003] Over the past three decades, foreign researchers have also proposed a series of technical methods for analyzing infant voice characteristics to meet different applications and purposes. Such as identifying potential neurological disorders or pathological states in...

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): G10L15/02G10L15/06G10L25/03G10L25/48
CPCG10L15/02G10L15/06G10L25/03G10L25/48
Inventor 何娅玲何宇新
Owner 深圳声联网科技有限公司
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