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

A voice recognition method and electronic device

A technology for electronic equipment and speech recognition, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of low recognition efficiency and difficult sound, and achieve the effect of improving the accuracy rate

Active Publication Date: 2020-07-24
GUANGDONG XIAOTIANCAI TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, more and more electronic devices on the market are equipped with voice recognition functions, and with the development of artificial intelligence, many electronic devices have a voice-activated wake-up function. Users can input preset voice information to wake up electronic devices, but electronic devices When the device sets up the sound model library, it is usually aimed at adults. The voice of adults is relatively stable and highly recognizable, and it can quickly complete the matching of adult voice information with the sound of the sound model library.
For students who are in the developmental period, the voice will change during the developmental period, making it relatively difficult and inefficient to identify the voices of developing students using an adult-oriented sound model library

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 recognition method and electronic device
  • A voice recognition method and electronic device
  • A voice recognition method and electronic device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] see figure 1 , figure 1 It is a schematic flowchart of a speech recognition method disclosed in an embodiment of the present invention. like figure 1 As shown, the speech recognition method may include the following steps:

[0067] 101. The electronic device extracts a target sound factor from a target voice pre-input by a user.

[0068] In the embodiment of the present invention, the electronic device may be a tutoring machine, a learning machine, a learning tablet, etc., which is not limited in this embodiment of the present invention. Users may be users of any age group and electronic devices of any age. The target voice may be the voice input by the user of the electronic device when using the electronic device for the first time, and the electronic device is made to generate a sound change curve according to the target voice. The voice factor may be a voiceprint node with unique characteristics in the user's voiceprint, and the number of voice factors matching...

Embodiment 2

[0084] see figure 2 , figure 2 It is a schematic flowchart of another speech recognition method disclosed in the embodiment of the present invention. like figure 2 As shown, the speech recognition method may include the following steps:

[0085] 201. The electronic device collects voice information of a large number of users, and the voice information at least includes sound factors corresponding to each age group of each user.

[0086] In the embodiment of the present invention, the voice information of a large number of users may be the voice information of all electronic device users collected by electronic devices, or may be obtained from third-party voice analysis software, which is not limited in this embodiment of the present invention.

[0087] In the embodiment of the present invention, each age group of the user can be divided by a preset time interval, or can be divided by the user himself, wherein the preset time interval can be one month, one year, two years...

Embodiment 3

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

[0119] Steps 301 to 302 are the same as steps 201 to 202, and the following content will not be repeated.

[0120] 303. The electronic device recognizes the voiceprint of the target voice input in advance by the user.

[0121] In the embodiment of the present invention, a voiceprint (Voiceprint) is a sound wave spectrum carrying language information, and the voiceprint is not only specific, but also relatively stable. After adulthood, the human voice can remain relatively stable for a long time, but during the developmental period, the human voice is usually in a state of change.

[0122] 304. The electronic device extracts several voiceprint nodes in the voiceprint.

[0123] In the embodiment of the present invention, the voiceprint no...

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 present invention relates to the technical field of electronic devices, and discloses a speech recognition method and an electronic device. The method comprises the steps of: extracting sound factors from sound input by a user in advance through an electronic device, and generating a user sound change curve by taking a sound factor as a basis according to a preset speech development rule model; and recognizing the current speech of the user according to the sound change curve through the electronic device. According to the embodiment of the invention, according to the user speech obtainedby the electronic device in advance and the sound factor in the speech, the speech development rule model is combined to generate the user sound change curve to allow the electronic device to accurately recognize the current sound of the user according to the user sound change curve so as to improve the accuracy of speech recognition of the electronic device.

Description

technical field [0001] The invention relates to the technical field of electronic equipment, in particular to a voice recognition method and electronic equipment. Background technique [0002] At present, more and more electronic devices on the market are equipped with voice recognition functions, and with the development of artificial intelligence, many electronic devices have a voice-activated wake-up function. Users can input preset voice information to wake up electronic devices, but electronic devices When the device sets up the sound model library, it is usually aimed at adults. The voice of adults is relatively stable and highly recognizable, and it can quickly complete the matching of adult voice information with the sound of the sound model library. For students in the developmental period, the voice will change during the developmental period, which makes it relatively difficult and inefficient to identify the voices of developing students using the sound model lib...

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): G10L15/02G10L15/06G10L15/065G10L15/26
CPCG10L15/02G10L15/06G10L15/065G10L15/26
Inventor 杨昊民
Owner GUANGDONG XIAOTIANCAI TECH CO LTD