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

A voice detection method and learning device

A voice detection and equipment technology, applied in the field of education, can solve the problems of lowering the accuracy rate of spelling words, failing to collect correct pronunciation of students, and limited time for collecting voices, etc., and achieve the effect of accurate detection of voice standards

Active Publication Date: 2022-05-03
GUANGDONG XIAOTIANCAI TECH CO LTD
View PDF21 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in practice, it is found that students may try to spell unfamiliar words multiple times. Due to the limited time for the current learning device to collect voice, the learning device may not be able to collect the correct pronunciation input by the student. It can be seen that the learning device may Correct the pronunciation of the words that students can read, thereby reducing the accuracy of the learning equipment in detecting the pronunciation standard of students' spelling words, and also reducing the learning efficiency of students

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
  • A voice detection method and learning device
  • A voice detection method and learning device
  • A voice detection method and learning device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] see figure 1 , figure 1 It is a schematic flowchart of a speech detection method disclosed in an embodiment of the present invention. Such as figure 1 As shown, the voice detection method may include the following steps:

[0074] 101. After detecting that the user's finger is in contact with the point-to-read page, the learning device collects the target sound in the environment where the learning device is located.

[0075] In the embodiment of the present invention, the learning device may be a tutor machine, a learning tablet, and the like. The user's finger is in contact with the reading page. It can be that the user's finger is in contact with the reading page (such as pressing, moving, or smearing). In the contact state, when the user's finger is separated from the reading page, the learning device does not collect the target sound. The point-to-read page may be a book page or a paper page, and may also be a display screen of a learning device, which is not l...

Embodiment 2

[0099] see figure 2 , figure 2 It is a schematic flowchart of another voice detection method disclosed in the embodiment of the present invention. Such as figure 2 As shown, the voice detection method may include the following steps:

[0100] 201. When it is detected that the user's finger is in contact with the click-to-read page, the learning device turns on the audio collection device of the learning device, so that the audio collection device collects sounds in the environment where the learning device is located.

[0101] In the embodiment of the present invention, the audio collection device may be a microphone, a sound pickup, etc., and all sounds existing in the environment where the learning device is located can be collected through the audio collection device.

[0102] 202. When detecting that the user's finger is not in contact with the click-to-read page, the learning device turns off the audio collection device to obtain the target sound collected by the au...

Embodiment 3

[0118] see image 3 , image 3 It is a schematic flowchart of another voice detection method disclosed in the embodiment of the present invention. Such as image 3 As shown, the voice detection method may include the following steps:

[0119] 301. After detecting that the user's finger is in contact with the point-to-read page, the learning device collects a target sound in the environment where the learning device is located.

[0120] 302. The learning device acquires a contact trace of the user's finger touching the click-to-read page.

[0121] 303. The learning device identifies the contact coordinates corresponding to the contact track on the point-and-read page.

[0122] In the embodiment of the present invention, the learning device can establish a plane Cartesian coordinate system based on the point-to-read page, and then obtain that any point in the point-to-read page corresponds to a unique coordinate, and also makes each text in the point-to-read page correspond ...

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 field of education technology, and discloses a voice detection method and a learning device, comprising: collecting the target sound in the environment where the learning device is located when detecting that the user's finger is in contact with the point-to-read page; The text information corresponding to the page contact position, and determine the standard pronunciation of the text information; select the speech segment that matches the standard pronunciation from the target sound; calculate the target similarity between the speech segment and the standard pronunciation, and detect whether there is a target similarity greater than the preset The target speech segment of similarity; if it exists, determine the pronunciation standard of the user's spelling text information. Implement the embodiment of the present invention, can select the speech segment that matches with the standard pronunciation based on the complete speech, so that the learning device detects the selected speech segment, thereby determining the standardization of the speech input by the user. It can be seen that implementing the above method can make learning The device is more accurate in detecting the voice standard.

Description

technical field [0001] The invention relates to the field of education technology, in particular to a voice detection method and a learning device. Background technique [0002] At present, most learning devices such as tutoring machines and learning tablets can detect the voice of students spelling words. The current voice detection method is usually: the learning device collects the voice of students spelling words within a certain period of time, and the collected voice Detect and correct the student's voice if there is an error in the voice. However, in practice, it is found that students may try to spell unfamiliar words multiple times. Due to the limited time for the current learning device to collect voice, the learning device may not be able to collect the correct pronunciation input by the student. It can be seen that the learning device may Pronunciation correction is performed on the words that students can read, thereby reducing the accuracy of the learning equi...

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 Patents(China)
IPC IPC(8): G09B5/04G10L25/51
CPCG09B5/04G10L25/51
Inventor 彭婕
Owner GUANGDONG XIAOTIANCAI TECH CO LTD