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

Intelligent recognition method for incomplete voice of elderly people

A technology of intelligent recognition and speech, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as difficult recognition, deep and stable voice, and strict accent

Pending Publication Date: 2020-12-11
JIANGSU HUIMING SCI & TECH
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In speech recognition technology, the acquisition of speech features is particularly important. Due to the aging of vocal organs, the elderly have problems such as strict accent, deep and stable speech, and difficult recognition. At this time, the traditional speech feature model cannot fully represent this problem. voice characteristics of the elderly

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
  • Intelligent recognition method for incomplete voice of elderly people
  • Intelligent recognition method for incomplete voice of elderly people
  • Intelligent recognition method for incomplete voice of elderly people

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0089] Such as figure 1 As shown, a method for intelligent recognition of incomplete speech of an elderly person is characterized in that it comprises the following steps:

[0090] Step S1, voice data preprocessing, collecting the original voice signal, and preprocessing it, which specifically includes the following steps,

[0091] Step S11, windowing and framing the speech signal;

[0092] Step S12, voice signal endpoint detection;

[0093] Step S13, using the signal subspace enhancement algorithm to enhance the speech;

[0094] Step S2, speech feature extraction, fusing the extracted feature parameters;

[0095] Step S3, establishing a speech acoustic model.

[0096] Specifically, a bandpass filter is firstly used as an anti-aliasing filter to suppress frequencies exceeding f in the speech signal s / 2(f s is the sampling frequency) for all aliasing frequency components to prevent aliasing interference from affecting the signal sampling work. The data processed by pre-...

Embodiment 2

[0169] The difference between this embodiment and Embodiment 1 is that the speech model in this embodiment adopts a DNN-HMM model.

[0170] An eye movement machine vision tracking device for the elderly, comprising an eye region extraction device, an eye movement feature positioning device and a fixation point positioning device; the eye region extraction device uses a monocular camera to collect video images, and the collected images Carry out grayscale processing, perform face detection, and extract the human eye area; the eye movement feature positioning device selects the center of the iris instead of the center of the pupil as the moving point, and uses a method of combining grayscale integral projection and image gradient to locate the center of the iris After the described fixation point positioning device calculates the iris center coordinates and the eye corner point coordinates through the previous two devices, calculate the coordinate offset vector between the two to...

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, and particularly relates to an intelligent recognition method for incomplete voice of elderly people. The intelligent recognition method for incomplete voice of elderly people comprises the following steps: S1, preprocessing voice data, acquiring an original voice signal, and preprocessing the original voice signal, specifically including windowing and framing of the voice signal; detecting voice signal endpoints; performing voice enhancement processing by adopting a signal subspace enhancement algorithm; S2, extracting voice features, and fusing the extracted feature parameters; and S3, establishing a voice acoustic model. According to the intelligent recognition technology for incomplete voice of elderly people, the problems of slight sound amplitude and great influence of environmental noise caused by aging of vocal organs of the elderly people can be reduced, and the voice features fused by adopting the sound parameters can be closer to the voice features of the elderly people, so that data comprehensively representing the voice features of the elderly people can be acquired, and the recognition degree of incomplete voice and fuzzy voice of the elderly people is improved.

Description

technical field [0001] The invention relates to the technical field of speech recognition, in particular to an intelligent recognition method for incomplete speech of the elderly. Background technique [0002] Due to the decline of physical functions of the elderly, their vocal organs will age, accompanied by problems such as serious accent, deep voice, and difficult recognition, which makes it difficult for nursing staff to understand the care needs of the elderly clearly and accurately. [0003] Speech recognition, that is, automatic speech recognition (Automatic Speech Recognition, ASR), in layman's terms is to convert speech into text. The history of speech recognition research can be traced back to 60 years ago. Vintsyuk proposed the Dynamic Time Warping algorithm (Dynamic Time Warping, DTW), which effectively solved the problem of how to compare speech of different durations, and became the mainstream method for speech recognition at that time. In the 1970s, with the ...

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): G10L15/02G10L15/04G10L15/05G10L15/16G10L15/14G10L15/06G10L15/07G10L25/24
CPCG10L15/02G10L15/04G10L15/05G10L15/16G10L15/142G10L15/144G10L15/063G10L15/07G10L25/24G10L2015/0631
Inventor 罗晓君杨金水孙瑜罗湘喜
Owner JIANGSU HUIMING SCI & TECH
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