Online examinee voice authentication recognition and state maintenance system, and recognition method

A voice authentication and state maintenance technology, applied in voice analysis, instruments, etc., can solve problems such as low recognition rate, and achieve the effect of improving recognition efficiency, accuracy and efficiency

Inactive Publication Date: 2020-11-27
杭州鹿扬科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

5. Environmental noise and interference have a serious impact on speech recognition, resulting in low recognition rate

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
  • Online examinee voice authentication recognition and state maintenance system, and recognition method
  • Online examinee voice authentication recognition and state maintenance system, and recognition method
  • Online examinee voice authentication recognition and state maintenance system, and recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Such as figure 1 As shown, the online examinee's voice authentication recognition and state maintenance system, the system includes: a voice collection unit, a voice preprocessing unit, a cross speech recognition unit and a state maintenance unit; the voice collection unit is configured to periodically collect the original Voice signal, the collected voice signal is stored; the voice pre-processing unit is configured to call the stored original voice signal, perform filtering and noise reduction processing on the original voice signal, and simultaneously process the noise-reduced voice signal Separation is carried out to obtain key speech parts and irrelevant speech parts respectively; the cross-speech recognition unit is configured to use two different recognition methods for cross-recognition of the key speech parts, respectively, to obtain the first recognition part and the second recognition part , and compare the first recognition part with the second recognition p...

Embodiment 2

[0033] On the basis of the previous embodiment, the speech preprocessing unit includes: a filtering noise reduction processing subunit and a speech signal separation subunit; the filtering noise reduction processing subunit is configured to perform filtering and noise reduction on the original speech signal The processing specifically includes: decomposing the voice signal to obtain a noise voice signal, an error voice signal and a basic voice signal; and performing noise voice signal suppression on the noise voice signal part, and performing voice signal compensation on the error voice signal part. On the basis of the voice signal, the final voice signal is obtained; first, the received voice signal is expressed by the following formula: P P =Asincos(0.5wt+1.5kx); its voice signal energy density is: Among them, A is the amplitude of the voice signal; w is the phase of the voice signal; t is the time parameter of the voice signal; k is the correction coefficient, which is any...

Embodiment 3

[0035] On the basis of the previous embodiment, the voice signal separation subunit is configured to separate the noise-reduced voice signal to obtain key voice parts and irrelevant voice parts respectively; specifically, it includes: pre-collected voice signals The analysis is carried out to obtain the change relationship of the irrelevant speech time interval, the key speech time interval and the cumulative probability of the voice signal; the noise-reduced voice signal is separated by using the obtained change relationship.

[0036] refer to Figure 5 , the time interval of the irrelevant speech and the time interval of the key speech change periodically, and with the increase of time, the cumulative probability will increase significantly. In this way, the speech signal can be separated according to a pre-established model or variation relationship. From the separated voice signal, the key voice part can be obtained. Recognizing key speech parts in the follow-up can sign...

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 belongs to the technical field of speech recognition and particularly relates to an online examinee speech authentication recognition and state maintenance system and recognition method.The system comprises a speech collection unit, a speech preprocessing unit, a cross speech recognition unit and a state maintenance unit, wherein the voice acquisition unit is configured to be used for periodically acquiring original voice signals and storing the acquired voice signals, the voice preprocessing unit is configured to call the stored original voice signal, perform filtering and noise reduction processing on the original voice signal, and separate the voice signal after noise reduction to obtain a key voice part and an irrelevant voice part respectively, and the cross speech recognition unit is configured to perform cross recognition on the key speech part by using two different recognition methods. The system is advantaged in that voice filtering and noise reduction are carried out on the collected voice signals, so subsequent recognition efficiency is further improved.

Description

technical field [0001] The invention belongs to the technical field of voice recognition, and in particular relates to an online examinee voice authentication recognition and state maintenance system and a recognition method. 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 inform...

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): G10L17/00G10L17/02G10L17/04G10L21/0208G10L21/0272
CPCG10L17/02G10L17/04G10L21/0208G10L21/0272
Inventor 不公告发明人
Owner 杭州鹿扬科技有限公司
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