Unlock instant, AI-driven research and patent intelligence for your innovation.

Voice recognition rate analysis device and method and storage medium

A technology of speech recognition and analysis device, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of difficult compatibility, low efficiency, and complicated operation steps, and achieve the effect of compatibility in the testing process.

Active Publication Date: 2020-08-07
FOSHAN UNIVERSITY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The latter arranges a large number of testers to repeatedly perform testing, recording, uploading data and statistical analysis on site. This testing method consumes a lot of human resources, and the actual operation steps are cumbersome and inefficient;
[0005] At present, there are still a small number of speech recognition devices tested by building hardware systems, but the parameters tested lack the value of judging, analyzing and measuring the performance of speech modules, and the hardware The structure is more complex;
[0006] Among the few hardware test systems currently in existence, most of the test objects are complete speech recognition products, so for different devices, the test is difficult to be compatible and the versatility is low

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
  • Voice recognition rate analysis device and method and storage medium
  • Voice recognition rate analysis device and method and storage medium
  • Voice recognition rate analysis device and method and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The idea, specific structure and technical effects of the present invention will be clearly and completely described below in conjunction with the embodiments and accompanying drawings, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The same reference numbers are used throughout the drawings to indicate the same or similar parts.

[0057] The present invention proposes a speech recognition rate analysis device, comprising:

[0058] The voice acquisition module is used to acquire the voice information that needs to be tested;

[0059] An operation request instruction acquisition module, configured to obtain user operation request instructions, the operation request instructions include distance test, noise test, offset value test and automatic test;

[0060]The ranging mo...

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 a voice recognition rate analysis device and method and a storage medium, and the method comprises the following steps: 201, obtaining an operation request instruction of a user, wherein the operation request instruction comprises distance testing, noise testing, offset value testing and automatic testing; 202, when the operation request instruction of the user is a distance test, controlling the distance measurement module to measure the distance between the tested voice module and the voice recognition rate analysis device; when the operation request instruction of the user is a noise test, controlling the noise test module to calculate the environment decibel, when the operation request instruction of the user is an offset value test, controlling the offset value test module to calculate the offset value of the voice information of the test, and when the operation request instruction of the user is an automatic test, automatically carrying out the test; and203, displaying the test result in the step 202 in a display module. And the method can better adapt to different to-be-tested devices, so that the test process is more compatible and more universal.

Description

technical field [0001] The invention relates to the field of data collection, in particular to a speech recognition rate analysis device, method and storage medium. Background technique [0002] As a very popular technology at present, speech recognition has been reasonably used by many industries. [0003] The reference value of speech recognition rate of existing speech products is low, because the lack of analysis of environmental parameters and functional parameters in the recognition state during the test process; [0004] There are two main methods for testing speech recognition rate: software simulation test and manual test. The former inputs audio signals to the voice module through software, and obtains test recognition results on the computer. This test method ignores human factors and environmental factors, and the results obtained are too ideal. The latter arranges a large number of testers to repeatedly perform testing, recording, uploading data and statistica...

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): G10L15/01G10L25/30
CPCG10L15/01G10L25/30
Inventor 潘浩贤蔡伟雄严冬冼佳莉陈南洲陈晓燕
Owner FOSHAN UNIVERSITY