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

Language recognition method of high-precision medical equipment for irregular sound of patient

A medical equipment and language recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as the inability of speech recognition system to recognize, and achieve the effect of good human-computer interaction experience.

Inactive Publication Date: 2021-11-12
深圳市云创精密医疗科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the above-mentioned shortcomings existing in the prior art, the present invention provides a high-precision medical equipment language recognition method aimed at irregular voices of patients, which solves the problems caused by the patient's slurred speech or the patient's speech when interacting with the medical equipment. The local language causes the speech recognition system of medical equipment to fail to recognize the problem

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
  • Language recognition method of high-precision medical equipment for irregular sound of patient
  • Language recognition method of high-precision medical equipment for irregular sound of patient
  • Language recognition method of high-precision medical equipment for irregular sound of patient

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] This embodiment discloses as figure 1 The shown language recognition method for high-precision medical equipment aimed at patients with irregular voices includes the following steps:

[0052] S1: The medical patient utters a voice, 10 in the original language.

[0053] S2: The receiving module 1 receives the speech signal and sends the speech signal to the signal processing module 2, and the signal processing module 2 processes it.

[0054] S3: The feature extraction module 4 performs feature extraction on the signal processed by the signal processing module 2 .

[0055] S4: Upload the extracted feature model to the model library 5, judge whether the extracted feature model exists in the model library 5, if it exists, go to S5, if not, go to S6.

[0056] S5: Match the model extracted by the feature extraction module 4 with the personalized model in the model library 5 through the model matching module 6 .

[0057] S6: Import the language signal generation preset mode...

Embodiment 2

[0068] This embodiment discloses a method for performing classification processing when the signal processing module performs signal processing:

[0069] The classification processing of the signal processing module includes fuzzy language processing, local language processing, and Mandarin processing.

[0070] The original language uttered by the patient is identified and classified. For example, if the patient is slurred, it will be processed through the fuzzy language processing module in the signal processing module; correspondingly, if the original language of the patient is a local language, it will be processed through the Local language processing module for processing. Compared with the method of directly receiving recognition, the classification recognition processing method has higher recognition efficiency.

Embodiment 3

[0072] This embodiment discloses as image 3 Shown is a method for extracting and processing speech signals by frame-by-frame extraction in a feature extraction module:

[0073] Frame extraction divides the signal processed by the signal processing module into several small segments of speech, and then divides the several small segments of speech into several states, and merges each small segment of speech and one of the states in each several states for recognition, thereby obtaining the speech feature model.

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 speech recognition, in particular to a speech recognition method of high-precision medical equipment for irregular sound of a patient. The method comprises the following steps: receiving an original language sent by the medical patient by a receiving module, sending a language signal to a signal processing module, processing the language signal by the signal processing module, carrying out further recognition processing by a feature extraction module, a model library and a model matching module, finally, transmitting the signal to an execution conversion module, and converting the signal into an execution instruction so as to realize voice interaction with medical equipment. The invention provides the efficient speech recognition method capable of continuously training and learning and carrying out speech recognition on irregular voices, such as fuzzy languages and local dialects, of different patients and establishing a personalized language model library. Compared with speech interaction of existing medical equipment, the efficiency of classified recognition processing is higher, and the man-machine interaction experience feeling of the user is better.

Description

technical field [0001] The invention relates to the technical field of voice recognition, in particular to a language recognition method for high-precision medical equipment aimed at irregular voices of patients. Background technique [0002] Speech recognition is an interdisciplinary subject. In the past two decades, speech recognition technology has made remarkable progress and has begun to move from the laboratory to the market. It is expected that in the next 10 years, speech recognition technology will enter various fields such as industry, home appliances, communications, automotive electronics, medical care, home services, and consumer electronics. The application of speech recognition and dictation machines in some fields was rated as one of the ten major events in computer development in 1997 by the American press. Many experts believe that speech recognition technology is one of the ten most important technological developments in the field of information technol...

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): G10L15/02G10L15/06G10L15/22
CPCG10L15/02G10L15/063G10L15/22G10L2015/223
Inventor 毛丹凤
Owner 深圳市云创精密医疗科技有限公司
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