Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Speech error correction processing method and device, device for speech error correction processing

A processing method and voice technology, applied in voice analysis, voice recognition, instruments, etc., can solve problems such as increased difficulty, inconvenient positioning, and long time, so as to shorten the time required for error correction, improve efficiency, and increase convenience. Effect

Active Publication Date: 2020-01-31
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, on an intelligent terminal with a limited screen size, when the user locates a certain character from the recognition results in text form, especially when inserting the editing cursor between two adjacent characters, there is a problem of inconvenient positioning.
Moreover, when the wrong position is far from the cursor position before modification, the difficulty of the above positioning will increase
Therefore, the existing manual error correction process will take a long time, which not only affects the efficiency of voice input, but also affects the convenience of error correction

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
  • Speech error correction processing method and device, device for speech error correction processing
  • Speech error correction processing method and device, device for speech error correction processing
  • Speech error correction processing method and device, device for speech error correction processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] refer to figure 1 , which shows a flow chart of the steps of Embodiment 1 of a speech error correction processing method according to the present invention, which may specifically include the following steps:

[0058] Step 101. When it is detected that there is a suspected error in the recognition result of the voice input by the user, output a prompt message corresponding to the error;

[0059]Step 102, acquiring the user's subsequent operations;

[0060] Step 103 , performing error correction processing on the recognition result according to the subsequent operation.

[0061] The embodiment of the present invention can be applied to any application program with voice interaction function, such as a browser, an input method APP (Application program, Application), a search APP, and a map APP. The voice error correction processing method provided by the embodiment of the present invention can be applied to an application environment corresponding to a client and a serv...

Embodiment 2

[0091] refer to figure 2 , which shows a flow chart of steps in Embodiment 2 of a speech error correction processing method according to the present invention, which may specifically include the following steps:

[0092] Step 201, when it is detected that there is a suspected error in the recognition result of the voice input by the user, output a prompt message corresponding to the error;

[0093] Step 202, acquiring the user's subsequent operations;

[0094] Step 203 , in response to the user's selection operation on the wrong error correction candidate result, performing error correction processing on the recognition result according to the error correction candidate result corresponding to the selection operation.

[0095] compared to figure 1 In the first embodiment of the method shown, the user’s subsequent operation in this embodiment may specifically include: the user’s selection operation on the erroneous error correction candidate result, wherein the selection ope...

Embodiment 3

[0123] refer to image 3 , which shows a flow chart of steps in Embodiment 3 of a voice error correction processing method according to the present invention, which may specifically include the following steps:

[0124] Step 301. When it is detected that there is a suspected error in the recognition result of the voice input by the user, output prompt information corresponding to the error;

[0125] Step 302, acquiring the user's subsequent operations; the user's subsequent operations may specifically include: error correction voice instructions;

[0126] Step 303, matching the recognition result of the error correction voice command with the preset error correction rules;

[0127] Step 304: When the recognition result of the error correction voice instruction matches the preset error correction rule, use the preset error correction operation corresponding to the preset error correction rule as the target correction corresponding to the error correction voice instruction. wr...

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

Embodiments of the invention provide an error correction method and device of voice, and a device used for voice error correction. The error correction method of voice concretely comprises steps of outputting prompt information corresponding to an error when an identification result of input voice of a user is suspected to have the error; obtaining subsequent operation of the user; and performing error correction of the identification result according to the subsequent operation. The embodiments of the invention save the process of finding an error in an identification result, so that the user is enable to conduct corresponding subsequent operation according to prompt information, thereby improving the voice input efficiency.

Description

technical field [0001] The invention relates to the technical field of speech processing, in particular to a speech error correction processing method, a speech error correction processing device, and a speech error correction processing device. Background technique [0002] At present, the rapid development of the mobile Internet has led to the widespread popularization of intelligent terminals such as smart phones and tablet computers. However, due to the limited screen size and touch screen buttons, it is very difficult to type on smart terminals, especially smart phones, or it is inconvenient to type on smart phones when users are driving. At this time, it is the most convenient and natural way for human-computer interaction , voice input method is gradually accepted by the majority of users. [0003] The existing speech input method mainly uses the acoustic model and the speech model obtained according to the training to find the recognition result that best matches th...

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): G10L15/10G10L15/14G10L15/16G10L15/34
CPCG10L15/10G10L15/14G10L15/16G10L15/34
Inventor 陈伟王砚峰李浩斌
Owner BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products