Intelligent speech recognition to semantic comprehension result statistical system and method

A technology of semantic understanding and intelligent speech, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as the inability to distinguish speech recognition accuracy test results from semantic understanding ability test results, and achieve the effect of improving efficiency

Pending Publication Date: 2019-03-08
易诚博睿(南京)科技有限公司
View PDF9 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a statistical system and method for the results from intelligent speech recognition to semantic understanding, to solve the problem that the accuracy test results of speech recognition and the ability test results of semantic understanding cannot be distinguished in the existing intelligent speech recognition test process question

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 speech recognition to semantic comprehension result statistical system and method
  • Intelligent speech recognition to semantic comprehension result statistical system and method
  • Intelligent speech recognition to semantic comprehension result statistical system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0052] Such as figure 2 As shown, a statistical method for the results from intelligent speech recognition to semantic understanding, including the following methods:

[0053] The test unit selects the voice to be tested and the voice recognition service API, and inputs the voice to be tested to the voice recognition service API,

[0054] Intelligently recognize the speech to be tested, and edit it into text as the recognition result, and compare the recognition result with the marked text in the speech to be tested, such as image 3 the comparison shown;

[0055] If the recognition result is consistent with the test text after comparison, the speech to be tested is used as the semantic test text;

[0056] Input the semantic test text into the semantic understanding service API, perform the semantic understanding test, compare the semantic checkpoints, and obtain the semantic understanding result;

[0057] Calculate and count the results of speech recognition rate and sema...

Embodiment 3

[0059] A method for statistics of results from intelligent speech recognition to semantic understanding, comprising the following methods:

[0060] Select the voice to be tested and the voice recognition service API, input the voice to be tested to the voice recognition service API,

[0061] Intelligently recognize the speech to be tested, and edit it into text as the recognition result, and compare the recognition result with the marked text in the speech to be tested;

[0062] If the recognition result is consistent with the test text after comparison, the speech to be tested is used as the semantic test text ( figure 2 middle is the semantic test text 1);

[0063] If the recognition result of speech recognition is inconsistent with the test text, the following processing methods are carried out: artificially listen to the speech to be tested, and if the artificial listening agrees with the result of intelligent recognition of the speech to be tested, then select the resul...

Embodiment 4

[0068] A method for statistics of results from intelligent speech recognition to semantic understanding, comprising the following methods:

[0069] Select the voice to be tested and the voice recognition service API, input the voice to be tested to the voice recognition service API,

[0070] Intelligently recognize the speech to be tested, and edit it into text as the recognition result, and compare the recognition result with the marked text in the speech to be tested;

[0071] If the recognition result is consistent with the test text after comparison, the speech to be tested is used as the semantic test text;

[0072] If the recognition result of speech recognition is inconsistent with the test text, the following processing methods are carried out: artificially listen to the speech to be tested, and if the artificial listening agrees with the result of intelligent recognition of the speech to be tested, then select the result of intelligent recognition; Identify the resul...

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 discloses an intelligent speech recognition to semantic comprehension result statistical system and method. The system includes a running state acquisition unit, a test voice selection unit, a response result acquisition unit, a test semantic acquisition unit and a test unit. An identification text which is closer to voice contents can be obtained by adopting the schemes; the accurate rates of semantic services can be calculated after contrast; and the system and method are convenient and fast, and can automatically see reports, so that efficiency can be greatly enhanced, and split speech and semantic test activities can be got together.

Description

technical field [0001] The invention relates to computer application technology, in particular to a statistical system and method for results from intelligent speech recognition to semantic understanding. Background technique [0002] With the increasing maturity of voice recognition technology, more and more smart home appliances and smart home devices are appearing in the market. These smart devices are based on voice recognition technology. Currently, it is troublesome to test these voice smart devices. The accuracy test and the ability test of semantic understanding cannot be clearly separated. When there is a problem in the final result, it cannot be quickly and accurately attributed to the problem of speech recognition or semantic understanding. [0003] From the time the user utters a sentence to getting a reply, if the answer is unsatisfactory, I don’t know where there is an inexplicable problem in the middle. For example, if you ask about frogs and tadpoles, they w...

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): G10L15/01G10L15/26
CPCG10L15/01G10L15/26
Inventor 马永飞王道宁马立民
Owner 易诚博睿(南京)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