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

Voice recognition method and device, electronic equipment and medium

A technology of speech recognition and electronic equipment, applied in speech recognition, speech analysis, instruments, etc., can solve the problem that real-time monitoring of the accuracy of the user's pronunciation can not be realized, and achieve the effect of improving the efficiency of speech correction

Pending Publication Date: 2021-02-02
BEIJING BYTEDANCE NETWORK TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing methods not only need to pre-store the correct pronunciation results, but also cannot realize the real-time monitoring of whether the user's pronunciation is accurate, and correct the user's pronunciation in time

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 method and device, electronic equipment and medium
  • Voice recognition method and device, electronic equipment and medium
  • Voice recognition method and device, electronic equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] figure 1 It is a flow chart of a speech recognition method provided by Embodiment 1 of the present disclosure. This embodiment is applicable to the situation of recognizing whether the user's pronunciation is accurate. / or implemented in the form of hardware.

[0031] Such as figure 1 Described, the method of the present embodiment comprises:

[0032] S110. Acquire the user's pronunciation of the target speech text read by the user, and generate a target speech text image of the target speech text.

[0033] Among them, the target voice text can be written texts such as books, newspapers or magazines that the user reads in daily life, or text reading materials displayed on the web page, or practice questions for language learning. The language of the target voice text can be It is made up of Chinese, other languages, or a combination of multiple languages. In the embodiment of the present invention, the type and language type of the target voice text are only explaine...

Embodiment 2

[0044] As a preferred embodiment of the above embodiment, figure 2 It is a flow chart of a voice recognition method provided in Embodiment 2 of the present disclosure.

[0045] Such as figure 2 As shown, the method includes:

[0046] S210. Acquire the user's pronunciation of the target speech text read by the user, and generate a target speech text image of the target speech text.

[0047] S220. Determine sentences in the target voice text by performing character recognition on the target voice text image.

[0048] S230. Determine whether the sentence in the target phonetic text contains polyphonic characters, and if so, acquire multiple pronunciations of the polyphonic characters.

[0049] Specifically, each word contained in the sentence in the target speech text needs to be queried for its corresponding pinyin in real time. The pinyin query is supported by a conventional dictionary, a network dictionary or a dictionary database. , then acquire multiple pronunciations ...

Embodiment 3

[0059] image 3 A schematic structural diagram of a speech recognition device provided by Embodiment 3 of the present disclosure, the device includes: a target speech text image generation module 310 , a sentence correct pronunciation acquisition module 320 and a speech recognition result determination module 330 .

[0060] Target voice text image generation module 310, for obtaining the user's pronunciation of the user's reciting target voice text, and generating the target voice text image of the target voice text;

[0061] The correct pronunciation acquisition module 320 of the sentence is used to determine the sentence in the target speech text according to the target speech text image, and obtain the correct pronunciation of the sentence in the target speech text;

[0062] A voice recognition result determining module 330, configured to determine the user's voice recognition result according to the user's pronunciation and the correct pronunciation of the sentence in the ...

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 embodiment of the invention discloses a voice recognition method and device, electronic equipment and a medium. The method comprises the steps of obtaining user pronunciation of a user reading a target voice text, and generating a target voice text image of the target voice text; determining a statement in the target voice text according to the target voice text image, and obtaining a correctpronunciation of the statement in the target voice text; and determining a voice recognition result of the user according to the pronunciation of the user and the correct pronunciation of the statement in the target voice text, and displaying the voice recognition result on the target voice text. According to the technical scheme, the problems that in the prior art, correct pronunciation results need to be prestored, whether the pronunciation of a user is accurate or not cannot be monitored in real time, and the pronunciation of the user cannot be corrected in time are solved, the accuracy ofthe pronunciation of the user is detected in real time, and the voice correction efficiency is improved.

Description

technical field [0001] The present disclosure relates to the technical field of voice recognition, and in particular, to a voice recognition method, device, electronic equipment and media. Background technique [0002] In people's daily life or study, language is the most important communication tool for human beings and the main way of expression for people to communicate. Human language is first formed in the form of speech, and speech plays a decisive supporting role in language. [0003] Generally speaking, to judge whether people's pronunciation is accurate, first, by obtaining the current voice of people reading the target file, the current voice is recognized to obtain the user's pronunciation, and the user's pronunciation is compared with the correct pronunciation stored in advance. The existing methods not only need to pre-store the correct pronunciation results, but also cannot monitor whether the user's pronunciation is accurate in real time, and correct the user...

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): G10L15/22G10L15/26
CPCG10L15/22G10L15/26
Inventor 不公告发明人
Owner BEIJING BYTEDANCE NETWORK TECH CO LTD